diff --git a/.dockerignore b/.dockerignore
new file mode 100644
index 0000000..b45fd65
--- /dev/null
+++ b/.dockerignore
@@ -0,0 +1,28 @@
+# Downloaded issuer PDFs and the corpus stay on the machine that built them
+# (ADR 0016). Nothing in the image needs them, and the image must never carry
+# them.
+data/
+
+.venv/
+logs/
+frontend/
+tests/
+scripts/
+docs/
+.playwright-mcp/
+.git/
+.github/
+.claude/
+.ruff_cache/
+.pytest_cache/
+.coverage
+**/__pycache__/
+**/*.py[cod]
+.env
+.env.*
+*.md
+# pyproject.toml declares it as the package readme, so hatchling needs it to
+# build the project itself.
+!README.md
+Makefile
+docker-compose.yml
diff --git a/.env.example b/.env.example
new file mode 100644
index 0000000..946f754
--- /dev/null
+++ b/.env.example
@@ -0,0 +1,23 @@
+# Copy to .env and fill in. Never commit .env.
+# Every setting and its default is in src/policypal/config.py; only the three
+# with no default are required.
+
+# --- Required ---
+DATABASE_URL=postgresql+psycopg://policypal:password@localhost:5432/policypal
+OPENAI_API_KEY=
+# A long random string, e.g. `python -c "import secrets; print(secrets.token_urlsafe(48))"`
+JWT_SECRET_KEY=
+
+# --- Optional ---
+# Live plan prices come from the CMS Marketplace API. Without a key, plan
+# search still works from the stored catalog; the prices are the stored
+# age-27 ones rather than the user's age.
+CMS_MARKETPLACE_API_KEY=
+
+# "production" switches logs to JSON on stdout as well as to a file.
+ENVIRONMENT=development
+LOG_LEVEL=INFO
+LOG_DIR=logs/backend
+
+# Where the browser app is served from. CORS allows this origin and no other.
+FRONTEND_ORIGIN=http://localhost:5173
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 389882b..3557345 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -85,6 +85,52 @@ jobs:
       - name: Dependency audit
         run: npm audit --audit-level=high
 
+  # Closes the first of ADR 0002's two deferred items. The image is built and
+  # scanned on every PR; pushing it anywhere is the deploy workflow's job.
+  image:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+
+      - uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
+
+      - name: Build the API image
+        uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
+        with:
+          context: .
+          load: true
+          tags: policypal-api:${{ github.sha }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+
+      # The PDFs and the corpus are local-only (ADR 0016) and .dockerignore
+      # excludes data/. A regression there would ship gigabytes of issuer
+      # documents, so it is checked rather than trusted.
+      - name: The image must carry no issuer documents
+        env:
+          IMAGE: policypal-api:${{ github.sha }}
+        run: |
+          set -euo pipefail
+          found=$(docker run --rm --entrypoint sh "$IMAGE" -c 'ls -A /app/data 2>/dev/null | wc -l')
+          test "$found" -eq 0 || { echo "data/ reached the image"; exit 1; }
+
+      # Trivy's own action installs its binary through a script that fails
+      # silently on the runner; its published image is pinned instead, the
+      # same way gitleaks is. `--input` on a saved tar means no docker socket
+      # has to be handed to the scanner.
+      - name: Scan the image
+        env:
+          IMAGE: policypal-api:${{ github.sha }}
+          # Pinned by digest: a tag can be moved to different bytes.
+          TRIVY: "aquasec/trivy:0.64.1@sha256:a8ca29078522f30393bdb34225e4c0994d38f37083be81a42da3a2a7e1488e9e"
+        run: |
+          set -euo pipefail
+          docker save "$IMAGE" -o "$RUNNER_TEMP/image.tar"
+          docker run --rm -v "$RUNNER_TEMP:/scan" "$TRIVY" image \
+            --input /scan/image.tar \
+            --format table --exit-code 1 --ignore-unfixed --severity HIGH,CRITICAL
+          rm -f "$RUNNER_TEMP/image.tar"
+
   secret-scan:
     runs-on: ubuntu-latest
     env:
diff --git a/CHANGELOG.md b/CHANGELOG.md
index eb45516..7fafe6a 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -4,6 +4,19 @@
 
 ### Added
 
+- A `Dockerfile` for the API, and a CI job that builds and scans the image
+  (ADR 0022) — the first of ADR 0002's two deferred items. Multi-stage, runs
+  as a non-root user, `torch` from PyTorch's CPU index on Linux so no CUDA
+  libraries ship, and both models baked in at their pinned revisions so a cold
+  start needs no HuggingFace call. CI runs the built image and fails if
+  `/app/data` is not empty: the issuer PDFs are local-only (ADR 0016) and a
+  `.dockerignore` regression would otherwise ship gigabytes of them unnoticed.
+  Trivy fails the build on fixable HIGH or CRITICAL findings.
+- `.env.example`, which did not exist: the three settings with no default
+  (`DATABASE_URL`, `OPENAI_API_KEY`, `JWT_SECRET_KEY`) and the handful worth
+  setting, with no values in it.
+- `make test`, `make lint` and `make check` run what CI runs, so passing
+  locally means the same thing.
 - Phase 4 live ingest: the catalog and SBCs for eighteen HealthCare.gov states
   — 3,276 plans from 137 issuers, every issuer's documents rather than the top
   parents'. 1,246 documents are stored and 1,940 plans (59.2%) have text behind
@@ -201,6 +214,13 @@
 
 ### Changed
 
+- In production the logs also go to stdout as JSON, where a container platform
+  collects them; a container's own filesystem is ephemeral and unread.
+  Development is unchanged, so an ingestion run's log lines do not interleave
+  with its progress output.
+- `tiktoken` and `anyio` are no longer dependencies. Neither was imported
+  anywhere; `tiktoken` in particular sat next to `core/text.py`'s deliberate
+  1.35×-word-count approximation looking like an unfinished intention.
 - The BM25 index is stored in the database, in `search_indexes`, instead of
   `data/corpus/indices/bm25.pkl` (ADR 0021, new migration). A missing index
   was a `FileNotFoundError` nothing caught, so an app running anywhere but the
diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000..c21f0e2
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,71 @@
+# The API only. Ingestion stays on the machine that holds data/ (ADR 0016,
+# 0019); nothing in this image fetches or keeps a PDF.
+FROM python:3.12-slim-bookworm@sha256:392307d22300de8b5986851a12d9176dfc0fc073e65bf6523ebd7dcbeb23564e AS builder
+
+# Every base and tool image is pinned by digest, not by tag: a tag can be
+# moved to different bytes, and the rest of this repo pins actions by SHA
+# and gitleaks by checksum for the same reason.
+COPY --from=ghcr.io/astral-sh/uv:0.11.23@sha256:d0a0a753ab981624b49c97abc98821c1c09f4ca69d1ef5cee69c501be3d88479 /uv /bin/uv
+
+ENV UV_COMPILE_BYTECODE=1 \
+    UV_LINK_MODE=copy \
+    UV_PYTHON_DOWNLOADS=never
+
+WORKDIR /app
+
+# Dependencies resolve from the lock alone, so this layer is rebuilt only when
+# the lock changes — not on every source edit. torch comes from PyTorch's CPU
+# index on linux (see pyproject.toml), which leaves out the CUDA libraries.
+COPY pyproject.toml uv.lock ./
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync --locked --no-dev --no-install-project
+
+COPY src/ ./src/
+COPY migrations/ ./migrations/
+COPY alembic.ini README.md ./
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync --locked --no-dev
+
+# Both models, at the revisions config.py pins, downloaded once here. A cold
+# start then loads them from the image instead of reaching HuggingFace, so a
+# HuggingFace outage cannot take the API down and no request waits on a
+# 220 MB download.
+# The venv's python directly, not `uv run`: `uv run` re-syncs the default
+# groups, which pulls the dev dependencies back in after --no-dev removed them.
+ENV HF_HOME=/opt/models
+RUN JWT_SECRET_KEY=build OPENAI_API_KEY=build DATABASE_URL=postgresql+psycopg://build/build \
+    /app/.venv/bin/python -c "\
+from sentence_transformers import CrossEncoder, SentenceTransformer; \
+from src.policypal.config import settings; \
+SentenceTransformer(settings.embedding_model, revision=settings.embedding_model_revision); \
+CrossEncoder(settings.reranker_model, revision=settings.reranker_model_revision)"
+
+
+FROM python:3.12-slim-bookworm@sha256:392307d22300de8b5986851a12d9176dfc0fc073e65bf6523ebd7dcbeb23564e AS runtime
+
+# Nothing here runs as root, and nothing writes to the image.
+RUN useradd --create-home --uid 10001 policypal
+
+ENV PATH="/app/.venv/bin:$PATH" \
+    PYTHONUNBUFFERED=1 \
+    PYTHONDONTWRITEBYTECODE=1 \
+    HF_HOME=/opt/models \
+    HF_HUB_OFFLINE=1 \
+    LOG_DIR=/tmp/logs
+
+WORKDIR /app
+
+COPY --from=builder --chown=policypal:policypal /app/.venv /app/.venv
+COPY --from=builder --chown=policypal:policypal /opt/models /opt/models
+COPY --chown=policypal:policypal src/ ./src/
+COPY --chown=policypal:policypal migrations/ ./migrations/
+COPY --chown=policypal:policypal alembic.ini ./
+
+USER policypal
+EXPOSE 8000
+
+# One worker: Flask-Limiter has no shared storage yet, so each worker would
+# keep its own counters and the configured limits would multiply (ADR 0022).
+# Threads carry the concurrency; the request path waits on OpenAI, not on CPU.
+CMD ["gunicorn", "--bind", "0.0.0.0:8000", "--workers", "1", "--threads", "8", \
+     "--timeout", "120", "--access-logfile", "-", "src.api.main:create_app()"]
diff --git a/README.md b/README.md
index 4ec97f5..6136d63 100644
--- a/README.md
+++ b/README.md
@@ -124,7 +124,34 @@ driven from the repo root:
 | `make ui-test` | Vitest |
 | `make ui-preview` | serves `frontend/dist` — run `make ui-build` first |
 
-Copy the required variables below into a `.env` file at the repo root before running the API.
+And what CI runs, in one command each:
+
+| Target | Runs |
+| --- | --- |
+| `make test` | pytest with the 85% coverage floor |
+| `make lint` | ruff |
+| `make check` | lint, tests, `alembic check`, bandit, pip-audit |
+
+Copy `.env.example` to `.env` at the repo root and fill in the three required values
+before running the API.
+
+### Running the API in a container
+
+```bash
+docker build -t policypal-api .
+docker run --rm -p 8000:8000 --env-file .env -e ENVIRONMENT=production policypal-api
+```
+
+The image carries the API only — ingestion, refresh and the reports stay on the machine
+that holds `data/` (ADR 0016, 0019), and `.dockerignore` keeps the issuer PDFs out of it.
+It needs no `data/` directory at all: the BM25 index comes from the database (ADR 0021)
+and both models are baked in at their pinned revisions, so a cold start makes no
+HuggingFace call. `torch` comes from PyTorch's CPU index on Linux, so no CUDA libraries
+ship (ADR 0022).
+
+It runs one gunicorn worker with eight threads. That is a deliberate ceiling, not a
+default: Flask-Limiter has no shared storage yet, so a second worker would keep its own
+counters and double the configured rate limits.
 
 > **macOS note:** AirPlay Receiver (Control Center) listens on `*:5000`. Flask still binds
 > `127.0.0.1:5000` alongside it, but `localhost` can resolve to `::1` and reach AirPlay instead —
diff --git a/docs/decisions/0022-the-api-as-a-container.md b/docs/decisions/0022-the-api-as-a-container.md
new file mode 100644
index 0000000..c46638a
--- /dev/null
+++ b/docs/decisions/0022-the-api-as-a-container.md
@@ -0,0 +1,119 @@
+# 0022 — The API as a container
+
+## Status
+
+Accepted. Closes the first of ADR 0002's two deferred items ("Docker build +
+image vulnerability scan. There is no Dockerfile for the app."). Depends on
+ADR 0021, without which the image cannot serve a request.
+
+## Context
+
+The app has only ever run on the machine that built its corpus. Everything
+that assumption hid had to be found before an image could work: ADR 0021 moved
+the BM25 index off local disk, and the API had never configured logging at
+all.
+
+Two properties of this app shape the image more than anything else:
+
+- **It carries a model runtime.** `torch`, `sentence-transformers` and two
+  models are in the request path, for the embedder and the cross-encoder.
+  `torch` alone is 553 MB of the 1.1 GB virtualenv.
+- **It must never carry the documents.** `data/sbc/` is 983 MB of issuers'
+  PDFs, kept forever and strictly local (ADR 0016, ADR 0019). An image that
+  shipped them would break that, quietly, at a gigabyte a time.
+
+## Decision
+
+### The image runs the API, and nothing else
+
+Ingestion, refresh and the reports stay on the machine that holds `data/`.
+Nothing in the image fetches a PDF, and `.dockerignore` excludes `data/`.
+
+**CI proves it rather than trusting it:** the built image is run and
+`/app/data` must be empty. A `.dockerignore` regression is otherwise invisible
+until an image is gigabytes too large.
+
+### torch comes from PyTorch's CPU index, on Linux only
+
+The default wheels bundle CUDA libraries that a CPU container cannot use.
+`pyproject.toml` points `torch` at `https://download.pytorch.org/whl/cpu`
+under `sys_platform == 'linux'`, so the image and CI get CPU wheels while
+macOS development is untouched. Re-locking removed every `nvidia-*` package
+and `triton`.
+
+### Both models are baked in at build time
+
+`SentenceTransformer` and `CrossEncoder` are instantiated during the build, at
+the revisions `config.py` pins, into `HF_HOME=/opt/models`. The runtime sets
+`HF_HUB_OFFLINE=1`.
+
+- A cold start loads them from the image instead of downloading ~220 MB.
+- **A HuggingFace outage cannot take the API down**, which it could if the
+  first request fetched them.
+- The pinned revisions are what ships, so the image is reproducible in the one
+  way ADR 0008 noted was weak.
+
+### One worker, several threads
+
+Flask-Limiter has no shared storage, so each worker would keep its own
+counters and the configured limits would multiply by worker count — the two
+that matter being 5/min on register and 10/min on login. Until there is a
+shared backend, the image runs **one** gunicorn worker.
+
+Threads carry the concurrency instead, which suits this app: a request waits
+on OpenAI and on Postgres, not on CPU. It also avoids paying for the model
+runtime N times over in memory.
+
+This is a real ceiling, not a preference, and it is the first thing to revisit
+when traffic justifies a Redis backend for the limiter.
+
+### Logs go to stdout in production
+
+`setup_logging()` wrote only to a rotating file. In a container that
+filesystem is ephemeral and nobody reads it. In production the root logger
+also writes JSON to stdout, where the platform collects it; in development it
+does not, so an ingestion run's log lines do not interleave with its own
+progress output.
+
+### Every image it depends on is pinned by digest
+
+The base image, the `uv` image the build copies from, and the Trivy image that
+scans the result are all pinned `name:tag@sha256:…`. A tag can be moved to
+different bytes; a digest cannot. This is the same standard the repository
+already applies to GitHub Actions (SHA-pinned) and to gitleaks (installed by
+checksum), and the reason is the same: a build that is reproducible only until
+someone else re-tags is not reproducible.
+
+### It does not run as root, and does not write to itself
+
+A `policypal` user owns the virtualenv and the source. `LOG_DIR` points at
+`/tmp`. The image has no shell-accessible secrets: every setting comes from
+the environment, and `.env.example` documents which ones with no values in it.
+
+## Consequences
+
+- **The image is 2.48 GB** — large by ordinary standards, and mostly the model
+  runtime: CPU torch, and 217 MB of baked weights. Verified in the built
+  image: `torch 2.14.0+cpu`, **zero** `nvidia-*` packages, no `ruff` or
+  `pytest`, running as `policypal`, and `/app` holding only `src`,
+  `migrations` and `alembic.ini`.
+- **Proved rather than assumed.** A container with no `data/` directory
+  (`Path('/app/data').exists()` is `False`) loads the BM25 index from Postgres
+  and answers "What is a deductible?" with the glossary entry at 0.999,
+  `HF_HUB_OFFLINE=1` throughout — so both models came from the image and no
+  request touched HuggingFace. Served over HTTP it returns the right counties
+  for a ZIP and 401 for an unauthenticated `/api/auth/me`, with access logs on
+  stdout.
+- **Building it is slow on a poor connection.** The model-baking step took
+  about 7 minutes here, almost all of it downloading from HuggingFace
+  unauthenticated. CI caches the layer, so it is paid once per lock or config
+  change, not per build.
+- **Cold starts load two models from disk.** Faster than downloading them, but
+  not free; scale-to-zero trades latency for cost, and the deployment ADR
+  decides that.
+- **A model change is an image rebuild**, which is the point: the revision in
+  `config.py` and the weights in the image cannot drift apart.
+- **The scan runs on every PR** and fails on fixable HIGH or CRITICAL findings.
+  A base-image CVE now breaks the build, which is the intended cost.
+- **CD is still not built.** That is ADR 0002's second deferred item and the
+  next decision.
diff --git a/pyproject.toml b/pyproject.toml
index 312c98d..a5a48c6 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -6,10 +6,10 @@ readme = "README.md"
 requires-python = ">=3.12"
 dependencies = [
     "alembic>=1.18.5",
-    "anyio>=4.14.2",
     "bcrypt>=5.0.0",
     "email-validator>=2.3.0",
     "flask>=3.1.3",
+    "gunicorn>=23.0.0",
     "flask-cors>=6.0.5",
     "flask-jwt-extended>=4.7.4",
     "flask-limiter>=4.1.1",
@@ -22,7 +22,6 @@ dependencies = [
     "rank-bm25>=0.2.2",
     "sentence-transformers>=5.6.0",
     "sqlalchemy>=2.0.51",
-    "tiktoken>=0.13.0",
     "torch>=2.12.1",
     "tqdm>=4.68.3",
     "transformers>=5.12.1",
@@ -50,3 +49,14 @@ dev = [
 
 [tool.pytest.ini_options]
 pythonpath = ["."]
+
+# torch ships CUDA libraries by default, which are several hundred megabytes of
+# dead weight in a CPU-only container. Linux (the image and CI) resolves from
+# PyTorch's CPU index; macOS keeps the default wheels, which are already CPU.
+[[tool.uv.index]]
+name = "pytorch-cpu"
+url = "https://download.pytorch.org/whl/cpu"
+explicit = true
+
+[tool.uv.sources]
+torch = [{ index = "pytorch-cpu", marker = "sys_platform == 'linux'" }]
diff --git a/src/core/logging.py b/src/core/logging.py
index 550bc52..b214f5b 100644
--- a/src/core/logging.py
+++ b/src/core/logging.py
@@ -31,6 +31,11 @@ def setup_logging() -> None:
 
     is_prod = settings.environment == "production"
 
+    # In a container the filesystem is ephemeral and nobody reads it; the
+    # platform collects stdout. Added only in production so a local ingestion
+    # run's log lines don't interleave with its own progress output.
+    handlers = ["file", "console"] if is_prod else ["file"]
+
     dictConfig({
         "version": 1,
         "disable_existing_loggers": False,
@@ -51,16 +56,21 @@ def setup_logging() -> None:
                 "backupCount": 5,               # keep app.log + 5 rotated copies
                 "encoding": "utf-8",
                 "formatter": "json" if is_prod else "console"
+            },
+            "console": {
+                "class": "logging.StreamHandler",
+                "stream": "ext://sys.stdout",
+                "formatter": "json" if is_prod else "console"
             }
         },
         "root": {
             "level": settings.log_level,
-            "handlers": ["file"]
+            "handlers": handlers
         },
         "loggers": {
             "sqlalchemy.engine": {
                 "level": "WARNING",
-                "handlers": ["file"],
+                "handlers": handlers,
                 "propagate": False
             },
             # At DEBUG these log request lines and bodies: urllib3 the CMS
diff --git a/src/core/text.py b/src/core/text.py
index 9ade1a6..0b94276 100644
--- a/src/core/text.py
+++ b/src/core/text.py
@@ -1,3 +1,9 @@
 def count_tokens(text: str) -> int:
-    """Approximate token count as 1.35x the word count."""
+    """Approximate token count as 1.35x the word count.
+
+    Deliberately an approximation, not a tokenizer. It decides chunk
+    boundaries, so switching to an exact count would re-chunk the corpus and
+    move every stored chunk_id — a re-ingest and a floor re-measure, to bound
+    a history budget and a chunk size that are both already generous.
+    """
     return int(len(text.split()) * 1.35)
diff --git a/tests/test_api_logging.py b/tests/test_api_logging.py
index 9661502..30ee799 100644
--- a/tests/test_api_logging.py
+++ b/tests/test_api_logging.py
@@ -8,6 +8,10 @@
 import logging
 from logging.handlers import RotatingFileHandler
 
+import pytest
+
+from src.core import logging as app_logging
+
 
 def test_creating_the_app_installs_the_file_handler(app):
     root = logging.getLogger()
@@ -24,3 +28,26 @@ def test_the_libraries_that_would_log_secrets_stay_at_warning(app):
     """urllib3 logs the CMS URL with its ?apikey=; httpx and openai log the prompt."""
     for name in ("urllib3", "httpx", "openai"):
         assert logging.getLogger(name).level == logging.WARNING
+
+
+@pytest.fixture
+def production(monkeypatch):
+    monkeypatch.setattr(app_logging.settings, "environment", "production")
+    yield
+    app_logging.setup_logging()   # put the development configuration back
+
+
+def _streams(root):
+    return [h for h in root.handlers if type(h) is logging.StreamHandler]
+
+
+def test_production_also_logs_to_stdout(production):
+    """A container's filesystem is ephemeral and unread; the platform collects stdout."""
+    app_logging.setup_logging()
+
+    assert _streams(logging.getLogger())
+
+
+def test_development_logs_only_to_the_file(app):
+    """Otherwise an ingestion run's log lines interleave with its own progress output."""
+    assert not _streams(logging.getLogger())
diff --git a/uv.lock b/uv.lock
index 9b896dc..471e1bb 100644
--- a/uv.lock
+++ b/uv.lock
@@ -1,6 +1,10 @@
 version = 1
 revision = 3
 requires-python = ">=3.12"
+resolution-markers = [
+    "sys_platform == 'linux'",
+    "sys_platform != 'linux'",
+]
 
 [[package]]
 name = "alembic"
@@ -500,81 +504,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/99/89/87ef49ffe383ef4e147d27b7bf2088fb0b54ea409dd87b5a89442e5828a5/cryptography-50.0.1-cp39-abi3-win_amd64.whl", hash = "sha256:55d16b1ef3ee0958d893a977b19777887e546c9954ea81b200c3301a864013f2", size = 3875429, upload-time = "2026-08-25T19:45:24.418Z" },
 ]
 
-[[package]]
-name = "cuda-bindings"
-version = "13.3.1"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "cuda-pathfinder" },
-]
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/ce/67/5e7dba1ba576dd73da5dee894ca076ca5e959450dfff66d6d510a255d1f7/cuda_bindings-13.3.1-cp312-cp312-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c7855c4868aabc0cfae28abbe83d56734bdfbd08f08fc234ac1912a12858bf49", size = 6025351, upload-time = "2026-05-29T23:11:49.685Z" },
-    { url = "https://files.pythonhosted.org/packages/39/2a/6d2e9047d1fb243dbaa364b01e0297534b9ed7fd27dba1c9f361519cf69b/cuda_bindings-13.3.1-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:e32d08f71ebcdf00f0f41eab2eb37e8da94c8ed411cc9f7f7a019ce6b34abe3a", size = 6657965, upload-time = "2026-05-29T23:11:52.227Z" },
-    { url = "https://files.pythonhosted.org/packages/cc/6e/2394f8163360f8391f8f1b7e72d300a82724edb81a7b7084c799fbd4c91f/cuda_bindings-13.3.1-cp313-cp313-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:9efb21c1ee64981e184b9e0ba5eb3179e5ba3d4b51665a6cb52b8ef3d01a7cbf", size = 5920504, upload-time = "2026-05-29T23:11:56.883Z" },
-    { url = "https://files.pythonhosted.org/packages/34/c2/ef9b6a63f7dc432712a462c816662e662e00d38caa9b861c8c2588195d03/cuda_bindings-13.3.1-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:2732904099e0a4d4db774a5fc6d91ee95fae065b4d2ecabb4968c5fe2406c9d7", size = 6476660, upload-time = "2026-05-29T23:11:59.188Z" },
-    { url = "https://files.pythonhosted.org/packages/b1/81/bff68ce829999c1e4209c761bbf903b1c06ec570416ddb25020864ad5907/cuda_bindings-13.3.1-cp314-cp314-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:1ab2f74ed65bfef4163ba07a8db16f1085e0729291db12a2423aff84ee8278b8", size = 6013639, upload-time = "2026-05-29T23:12:03.509Z" },
-    { url = "https://files.pythonhosted.org/packages/d4/e0/c8a1f0c8f9ffdea4f5fe6dbab89b326cef4d85caf489dad39e209da89416/cuda_bindings-13.3.1-cp314-cp314-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:efd4c814d311ec08c981f6dded1dbe7d4b371067ee4f6c14cccec4bde9590f80", size = 6534419, upload-time = "2026-05-29T23:12:05.633Z" },
-    { url = "https://files.pythonhosted.org/packages/52/b8/83b1f563925b290f2d11a01a77a84013ba56052fe3653a5bef3ccfbb43d6/cuda_bindings-13.3.1-cp314-cp314t-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c3c772dfff49681541d59630c90f858e173ac926b9c593a2b7123f2a1043cc76", size = 5809771, upload-time = "2026-05-29T23:12:10.422Z" },
-    { url = "https://files.pythonhosted.org/packages/12/20/e79b4bfe98f075195afb6343d41c498f9dbd2d161d7021d4d28bceb83581/cuda_bindings-13.3.1-cp314-cp314t-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:36febb7c1079d68a981dbbd8d5a67235b399802b82075c9388624719607e52b9", size = 6358584, upload-time = "2026-05-29T23:12:12.767Z" },
-]
-
-[[package]]
-name = "cuda-pathfinder"
-version = "1.5.5"
-source = { registry = "https://pypi.org/simple" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/11/c8/26f2e4aae92f11522a96043892ba39a90eac610d5242523aa863212bc1c7/cuda_pathfinder-1.5.5-py3-none-any.whl", hash = "sha256:0228c023f95d1480f143ef5c8922d27a2ab052087a942e81dc289c9eb8f91689", size = 51671, upload-time = "2026-05-27T01:21:25.413Z" },
-]
-
-[[package]]
-name = "cuda-toolkit"
-version = "13.0.3.0"
-source = { registry = "https://pypi.org/simple" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/d1/c7/a79086a62c98befcdb8349656c6f114e2db3b8b2422f6e25c97a7f2a9a3c/cuda_toolkit-13.0.3.0-py2.py3-none-any.whl", hash = "sha256:d693caaa261214ddd7dbb60d68e71cbed884e68c2be7509778f3051da0b91c3f", size = 2512, upload-time = "2026-04-14T00:50:08.173Z" },
-]
-
-[package.optional-dependencies]
-cublas = [
-    { name = "nvidia-cublas", marker = "(platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine == 'AMD64' and sys_platform == 'win32')" },
-    { name = "nvidia-cuda-nvrtc", marker = "(platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine == 'AMD64' and sys_platform == 'win32')" },
-]
-cudart = [
-    { name = "nvidia-cuda-runtime", marker = "(platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine == 'AMD64' and sys_platform == 'win32')" },
-]
-cufft = [
-    { name = "nvidia-cufft", marker = "(platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine == 'AMD64' and sys_platform == 'win32')" },
-    { name = "nvidia-nvjitlink", marker = "(platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine == 'AMD64' and sys_platform == 'win32')" },
-]
-cufile = [
-    { name = "nvidia-cufile", marker = "(platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux')" },
-]
-cupti = [
-    { name = "nvidia-cuda-cupti", marker = "(platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine == 'AMD64' and sys_platform == 'win32')" },
-]
-curand = [
-    { name = "nvidia-curand", marker = "(platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine == 'AMD64' and sys_platform == 'win32')" },
-]
-cusolver = [
-    { name = "nvidia-cublas", marker = "(platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine == 'AMD64' and sys_platform == 'win32')" },
-    { name = "nvidia-cusolver", marker = "(platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine == 'AMD64' and sys_platform == 'win32')" },
-    { name = "nvidia-cusparse", marker = "(platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine == 'AMD64' and sys_platform == 'win32')" },
-    { name = "nvidia-nvjitlink", marker = "(platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine == 'AMD64' and sys_platform == 'win32')" },
-]
-cusparse = [
-    { name = "nvidia-cusparse", marker = "(platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine == 'AMD64' and sys_platform == 'win32')" },
-    { name = "nvidia-nvjitlink", marker = "(platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine == 'AMD64' and sys_platform == 'win32')" },
-]
-nvjitlink = [
-    { name = "nvidia-nvjitlink", marker = "(platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine == 'AMD64' and sys_platform == 'win32')" },
-]
-nvrtc = [
-    { name = "nvidia-cuda-nvrtc", marker = "(platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine == 'AMD64' and sys_platform == 'win32')" },
-]
-nvtx = [
-    { name = "nvidia-nvtx", marker = "(platform_machine == 'aarch64' and sys_platform == 'linux') or (platform_machine == 'x86_64' and sys_platform == 'linux') or (platform_machine == 'AMD64' and sys_platform == 'win32')" },
-]
-
 [[package]]
 name = "cyclonedx-python-lib"
 version = "11.12.0"
@@ -814,6 +743,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/b4/0d/ca7d15afbdc397e3401134c9e1800d51d12b829661786187a4ad08fe484f/greenlet-3.5.3-cp315-cp315t-win_arm64.whl", hash = "sha256:b7068bd09f761f3f5b4d214c2bed063186b2a86148c740b3873e3f56d79bac31", size = 242586, upload-time = "2026-06-26T18:23:37.93Z" },
 ]
 
+[[package]]
+name = "gunicorn"
+version = "26.2.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/d9/8a/e4ef6ee11701b6cd64702848415ffb69eeff85cb388a3c6c7fe86f22f3f8/gunicorn-26.2.0.tar.gz", hash = "sha256:62b864895d9ebff0b2f9867ba04fe811c93121596540830c9c916d0769668447", size = 787921, upload-time = "2026-08-24T15:05:59.3Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/fe/85/7522a52e5e2f42faf1a129113ab63e548c42e103e9af395b7bfe65e403e2/gunicorn-26.2.0-py3-none-any.whl", hash = "sha256:bd249d0b3f7972f7432f0a6b6ff3b3ee2d129f70cd1ff6c09a9dd9e29a2b88e3", size = 228389, upload-time = "2026-08-24T15:05:57.67Z" },
+]
+
 [[package]]
 name = "h11"
 version = "0.16.0"
@@ -1571,158 +1509,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/fd/6a/d3a169aaf8536cf228d56a09e04bcb713a2fe4410d4e2105b9419b5a9c89/numpy-2.5.0-cp314-cp314t-win_arm64.whl", hash = "sha256:016623417bb330d719d579daf2d6b9a01ddc52e41a9ed61a47f39fde46dcd865", size = 10686451, upload-time = "2026-06-21T20:57:49.313Z" },
 ]
 
-[[package]]
-name = "nvidia-cublas"
-version = "13.1.1.3"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "nvidia-cuda-nvrtc" },
-]
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/a7/a1/0bd24ee8c8d03adac032fd2909426a00c88f8c57961b1277ded97f91119f/nvidia_cublas-13.1.1.3-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:b7a210458267ac818974c53038fbec2e969d5c99f305ab15c72522fa9f001dd5", size = 542848918, upload-time = "2026-04-08T18:46:22.985Z" },
-    { url = "https://files.pythonhosted.org/packages/3b/cd/154ca20c38269e05eff77c1464e6c1da89f50a6390b565e9d82e06bc11e1/nvidia_cublas-13.1.1.3-py3-none-manylinux_2_27_x86_64.whl", hash = "sha256:37936a16db8fe4ac1f065c2139360608a543a09275cb1a1af612e08cfa065436", size = 423138758, upload-time = "2026-04-08T18:46:58.655Z" },
-]
-
-[[package]]
-name = "nvidia-cuda-cupti"
-version = "13.0.85"
-source = { registry = "https://pypi.org/simple" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/2a/2a/80353b103fc20ce05ef51e928daed4b6015db4aaa9162ed0997090fe2250/nvidia_cuda_cupti-13.0.85-py3-none-manylinux_2_25_aarch64.whl", hash = "sha256:796bd679890ee55fb14a94629b698b6db54bcfd833d391d5e94017dd9d7d3151", size = 10310827, upload-time = "2025-09-04T08:26:42.012Z" },
-    { url = "https://files.pythonhosted.org/packages/33/6d/737d164b4837a9bbd202f5ae3078975f0525a55730fe871d8ed4e3b952b0/nvidia_cuda_cupti-13.0.85-py3-none-manylinux_2_25_x86_64.whl", hash = "sha256:4eb01c08e859bf924d222250d2e8f8b8ff6d3db4721288cf35d14252a4d933c8", size = 10715597, upload-time = "2025-09-04T08:26:51.312Z" },
-]
-
-[[package]]
-name = "nvidia-cuda-nvrtc"
-version = "13.0.88"
-source = { registry = "https://pypi.org/simple" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/c3/68/483a78f5e8f31b08fb1bb671559968c0ca3a065ac7acabfc7cee55214fd6/nvidia_cuda_nvrtc-13.0.88-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:ad9b6d2ead2435f11cbb6868809d2adeeee302e9bb94bcf0539c7a40d80e8575", size = 90215200, upload-time = "2025-09-04T08:28:44.204Z" },
-    { url = "https://files.pythonhosted.org/packages/b7/dc/6bb80850e0b7edd6588d560758f17e0550893a1feaf436807d64d2da040f/nvidia_cuda_nvrtc-13.0.88-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:d27f20a0ca67a4bb34268a5e951033496c5b74870b868bacd046b1b8e0c3267b", size = 43015449, upload-time = "2025-09-04T08:28:20.239Z" },
-]
-
-[[package]]
-name = "nvidia-cuda-runtime"
-version = "13.0.96"
-source = { registry = "https://pypi.org/simple" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/87/4f/17d7b9b8e285199c58ce28e31b5c5bbaa4d8271af06a89b6405258245de2/nvidia_cuda_runtime-13.0.96-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:ef9bcbe90493a2b9d810e43d249adb3d02e98dd30200d86607d8d02687c43f55", size = 2261060, upload-time = "2025-10-09T08:55:15.78Z" },
-    { url = "https://files.pythonhosted.org/packages/2e/24/d1558f3b68b1d26e706813b1d10aa1d785e4698c425af8db8edc3dced472/nvidia_cuda_runtime-13.0.96-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:7f82250d7782aa23b6cfe765ecc7db554bd3c2870c43f3d1821f1d18aebf0548", size = 2243632, upload-time = "2025-10-09T08:55:36.117Z" },
-]
-
-[[package]]
-name = "nvidia-cudnn-cu13"
-version = "9.24.0.43"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "nvidia-cublas" },
-]
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/ca/30/7c257e3d5cb4fecb147b93895c66e29c93f8e76d74b45bb418ff0587c4ec/nvidia_cudnn_cu13-9.24.0.43-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:a6812a554a1ff0413e9c52b84c26c050380649ab9615f9c16bded368ce9f421f", size = 650976863, upload-time = "2026-07-02T16:23:39.248Z" },
-    { url = "https://files.pythonhosted.org/packages/5c/ba/791cffd048fe5b044e620df55267e3e95c0e6e07d50b41e377c03dfc910f/nvidia_cudnn_cu13-9.24.0.43-py3-none-manylinux_2_27_x86_64.whl", hash = "sha256:71f181cd810e90f9b6023b01186fe82d13d65f0ec098581ee201d39fad769e4b", size = 553099438, upload-time = "2026-07-02T16:27:42.58Z" },
-]
-
-[[package]]
-name = "nvidia-cufft"
-version = "12.0.0.61"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "nvidia-nvjitlink" },
-]
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/8b/ae/f417a75c0259e85c1d2f83ca4e960289a5f814ed0cea74d18c353d3e989d/nvidia_cufft-12.0.0.61-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:2708c852ef8cd89d1d2068bdbece0aa188813a0c934db3779b9b1faa8442e5f5", size = 214053554, upload-time = "2025-09-04T08:31:38.196Z" },
-    { url = "https://files.pythonhosted.org/packages/a8/2f/7b57e29836ea8714f81e9898409196f47d772d5ddedddf1592eadb8ab743/nvidia_cufft-12.0.0.61-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:6c44f692dce8fd5ffd3e3df134b6cdb9c2f72d99cf40b62c32dde45eea9ddad3", size = 214085489, upload-time = "2025-09-04T08:31:56.044Z" },
-]
-
-[[package]]
-name = "nvidia-cufile"
-version = "1.15.1.6"
-source = { registry = "https://pypi.org/simple" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/3f/70/4f193de89a48b71714e74602ee14d04e4019ad36a5a9f20c425776e72cd6/nvidia_cufile-1.15.1.6-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:08a3ecefae5a01c7f5117351c64f17c7c62efa5fffdbe24fc7d298da19cd0b44", size = 1223672, upload-time = "2025-09-04T08:32:22.779Z" },
-    { url = "https://files.pythonhosted.org/packages/ab/73/cc4a14c9813a8a0d509417cf5f4bdaba76e924d58beb9864f5a7baceefbf/nvidia_cufile-1.15.1.6-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:bdc0deedc61f548bddf7733bdc216456c2fdb101d020e1ab4b88d232d5e2f6d1", size = 1136992, upload-time = "2025-09-04T08:32:14.119Z" },
-]
-
-[[package]]
-name = "nvidia-curand"
-version = "10.4.0.35"
-source = { registry = "https://pypi.org/simple" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/1e/72/7c2ae24fb6b63a32e6ae5d241cc65263ea18d08802aaae087d9f013335a2/nvidia_curand-10.4.0.35-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:133df5a7509c3e292aaa2b477afd0194f06ce4ea24d714d616ff36439cee349a", size = 61962106, upload-time = "2025-08-04T10:21:41.128Z" },
-    { url = "https://files.pythonhosted.org/packages/a5/9f/be0a41ca4a4917abf5cb9ae0daff1a6060cc5de950aec0396de9f3b52bc5/nvidia_curand-10.4.0.35-py3-none-manylinux_2_27_x86_64.whl", hash = "sha256:1aee33a5da6e1db083fe2b90082def8915f30f3248d5896bcec36a579d941bfc", size = 59544258, upload-time = "2025-08-04T10:22:03.992Z" },
-]
-
-[[package]]
-name = "nvidia-cusolver"
-version = "12.0.4.66"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "nvidia-cublas" },
-    { name = "nvidia-cusparse" },
-    { name = "nvidia-nvjitlink" },
-]
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/c8/c3/b30c9e935fc01e3da443ec0116ed1b2a009bb867f5324d3f2d7e533e776b/nvidia_cusolver-12.0.4.66-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:02c2457eaa9e39de20f880f4bd8820e6a1cfb9f9a34f820eb12a155aa5bc92d2", size = 223467760, upload-time = "2025-09-04T08:33:04.222Z" },
-    { url = "https://files.pythonhosted.org/packages/5f/67/cba3777620cdacb99102da4042883709c41c709f4b6323c10781a9c3aa34/nvidia_cusolver-12.0.4.66-py3-none-manylinux_2_27_x86_64.whl", hash = "sha256:0a759da5dea5c0ea10fd307de75cdeb59e7ea4fcb8add0924859b944babf1112", size = 200941980, upload-time = "2025-09-04T08:33:22.767Z" },
-]
-
-[[package]]
-name = "nvidia-cusparse"
-version = "12.6.3.3"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "nvidia-nvjitlink" },
-]
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/f8/94/5c26f33738ae35276672f12615a64bd008ed5be6d1ebcb23579285d960a9/nvidia_cusparse-12.6.3.3-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:80bcc4662f23f1054ee334a15c72b8940402975e0eab63178fc7e670aa59472c", size = 162155568, upload-time = "2025-09-04T08:33:42.864Z" },
-    { url = "https://files.pythonhosted.org/packages/fa/18/623c77619c31d62efd55302939756966f3ecc8d724a14dab2b75f1508850/nvidia_cusparse-12.6.3.3-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:2b3c89c88d01ee0e477cb7f82ef60a11a4bcd57b6b87c33f789350b59759360b", size = 145942937, upload-time = "2025-09-04T08:33:58.029Z" },
-]
-
-[[package]]
-name = "nvidia-cusparselt-cu13"
-version = "0.8.1"
-source = { registry = "https://pypi.org/simple" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/46/e1/cdc1797eadf82d3a9a575a19b33fdc871a97edbec42c00b5b5e914f4aff4/nvidia_cusparselt_cu13-0.8.1-py3-none-manylinux2014_aarch64.whl", hash = "sha256:4dca476c50bf4780d46cd0bfbd82e2bc10a08e4fef7950917ce8d7578d22a23f", size = 221051344, upload-time = "2025-09-05T18:49:51.289Z" },
-    { url = "https://files.pythonhosted.org/packages/34/7d/2661f2fb3ac4302f3a246f5fc030213ac60c1fe0bce84f9783dbd831dbb7/nvidia_cusparselt_cu13-0.8.1-py3-none-manylinux2014_x86_64.whl", hash = "sha256:786ce87568c303fadb5afcc7102d454cd3040d75f6f8626f5db460d1871f4dd0", size = 170148586, upload-time = "2025-09-05T18:50:50.248Z" },
-]
-
-[[package]]
-name = "nvidia-nccl-cu13"
-version = "2.30.7"
-source = { registry = "https://pypi.org/simple" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/d1/21/a73174c6157101bdf1ffc22b517f76ff0082613989dd9bc8f43e8034caac/nvidia_nccl_cu13-2.30.7-py3-none-manylinux_2_18_aarch64.whl", hash = "sha256:ca786ffa5a647c75d4d1f5cc72a6c4f537947e2ba8823d7c8aaf768e7a7b9f77", size = 215983881, upload-time = "2026-06-09T03:23:15.633Z" },
-    { url = "https://files.pythonhosted.org/packages/3f/34/c500f90c7ae641b8e0f98965b36b8a7ac79cc8b296e8d251fe3eb592ee54/nvidia_nccl_cu13-2.30.7-py3-none-manylinux_2_18_x86_64.whl", hash = "sha256:cefa7fdb9710efd0f39c5f1be1d61ff6fc9a996c451265bd7fbdcf9455ed4b50", size = 215965170, upload-time = "2026-06-09T03:23:39.73Z" },
-]
-
-[[package]]
-name = "nvidia-nvjitlink"
-version = "13.0.88"
-source = { registry = "https://pypi.org/simple" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/56/7a/123e033aaff487c77107195fa5a2b8686795ca537935a24efae476c41f05/nvidia_nvjitlink-13.0.88-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:13a74f429e23b921c1109976abefacc69835f2f433ebd323d3946e11d804e47b", size = 40713933, upload-time = "2025-09-04T08:35:43.553Z" },
-    { url = "https://files.pythonhosted.org/packages/ab/2c/93c5250e64df4f894f1cbb397c6fd71f79813f9fd79d7cd61de3f97b3c2d/nvidia_nvjitlink-13.0.88-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:e931536ccc7d467a98ba1d8b89ff7fa7f1fa3b13f2b0069118cd7f47bff07d0c", size = 38768748, upload-time = "2025-09-04T08:35:20.008Z" },
-]
-
-[[package]]
-name = "nvidia-nvshmem-cu13"
-version = "3.4.5"
-source = { registry = "https://pypi.org/simple" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/dc/0f/05cc9c720236dcd2db9c1ab97fff629e96821be2e63103569da0c9b72f19/nvidia_nvshmem_cu13-3.4.5-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:6dc2a197f38e5d0376ad52cd1a2a3617d3cdc150fd5966f4aee9bcebb1d68fe9", size = 60215947, upload-time = "2025-09-06T00:32:20.022Z" },
-    { url = "https://files.pythonhosted.org/packages/3c/35/a9bf80a609e74e3b000fef598933235c908fcefcef9026042b8e6dfde2a9/nvidia_nvshmem_cu13-3.4.5-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:290f0a2ee94c9f3687a02502f3b9299a9f9fe826e6d0287ee18482e78d495b80", size = 60412546, upload-time = "2025-09-06T00:32:41.564Z" },
-]
-
-[[package]]
-name = "nvidia-nvtx"
-version = "13.0.85"
-source = { registry = "https://pypi.org/simple" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/c2/f3/d86c845465a2723ad7e1e5c36dcd75ddb82898b3f53be47ebd429fb2fa5d/nvidia_nvtx-13.0.85-py3-none-manylinux1_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:4936d1d6780fbe68db454f5e72a42ff64d1fd6397df9f363ae786930fd5c1cd4", size = 148047, upload-time = "2025-09-04T08:29:01.761Z" },
-    { url = "https://files.pythonhosted.org/packages/a8/64/3708a90d1ebe202ffdeb7185f878a3c84d15c2b2c31858da2ce0583e2def/nvidia_nvtx-13.0.85-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:cb7780edb6b14107373c835bf8b72e7a178bac7367e23da7acb108f973f157a6", size = 148878, upload-time = "2025-09-04T08:28:53.627Z" },
-]
-
 [[package]]
 name = "openai"
 version = "3.13.0"
@@ -2030,13 +1816,13 @@ version = "0.1.0"
 source = { editable = "." }
 dependencies = [
     { name = "alembic" },
-    { name = "anyio" },
     { name = "bcrypt" },
     { name = "email-validator" },
     { name = "flask" },
     { name = "flask-cors" },
     { name = "flask-jwt-extended" },
     { name = "flask-limiter" },
+    { name = "gunicorn" },
     { name = "langchain-text-splitters" },
     { name = "openai" },
     { name = "pdfplumber" },
@@ -2048,8 +1834,8 @@ dependencies = [
     { name = "requests" },
     { name = "sentence-transformers" },
     { name = "sqlalchemy" },
-    { name = "tiktoken" },
-    { name = "torch" },
+    { name = "torch", version = "2.14.0", source = { registry = "https://pypi.org/simple" }, marker = "sys_platform != 'linux'" },
+    { name = "torch", version = "2.14.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform == 'linux'" },
     { name = "tqdm" },
     { name = "transformers" },
     { name = "wikipedia-api" },
@@ -2068,13 +1854,13 @@ dev = [
 [package.metadata]
 requires-dist = [
     { name = "alembic", specifier = ">=1.18.5" },
-    { name = "anyio", specifier = ">=4.14.2" },
     { name = "bcrypt", specifier = ">=5.0.0" },
     { name = "email-validator", specifier = ">=2.3.0" },
     { name = "flask", specifier = ">=3.1.3" },
     { name = "flask-cors", specifier = ">=6.0.5" },
     { name = "flask-jwt-extended", specifier = ">=4.7.4" },
     { name = "flask-limiter", specifier = ">=4.1.1" },
+    { name = "gunicorn", specifier = ">=23.0.0" },
     { name = "langchain-text-splitters", specifier = ">=1.1.2" },
     { name = "openai", specifier = ">=3.13.0" },
     { name = "pdfplumber", specifier = ">=0.11.10" },
@@ -2086,8 +1872,8 @@ requires-dist = [
     { name = "requests", specifier = ">=2.32.0" },
     { name = "sentence-transformers", specifier = ">=5.6.0" },
     { name = "sqlalchemy", specifier = ">=2.0.51" },
-    { name = "tiktoken", specifier = ">=0.13.0" },
-    { name = "torch", specifier = ">=2.12.1" },
+    { name = "torch", marker = "sys_platform != 'linux'", specifier = ">=2.12.1" },
+    { name = "torch", marker = "sys_platform == 'linux'", specifier = ">=2.12.1", index = "https://download.pytorch.org/whl/cpu" },
     { name = "tqdm", specifier = ">=4.68.3" },
     { name = "transformers", specifier = ">=5.12.1" },
     { name = "wikipedia-api", specifier = ">=0.15.0" },
@@ -2828,7 +2614,8 @@ dependencies = [
     { name = "numpy" },
     { name = "scikit-learn" },
     { name = "scipy" },
-    { name = "torch" },
+    { name = "torch", version = "2.14.0", source = { registry = "https://pypi.org/simple" }, marker = "sys_platform != 'linux'" },
+    { name = "torch", version = "2.14.0+cpu", source = { registry = "https://download.pytorch.org/whl/cpu" }, marker = "sys_platform == 'linux'" },
     { name = "tqdm" },
     { name = "transformers" },
     { name = "typing-extensions" },
@@ -2977,53 +2764,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/32/d5/f9a850d79b0851d1d4ef6456097579a9005b31fea68726a4ae5f2d82ddd9/threadpoolctl-3.6.0-py3-none-any.whl", hash = "sha256:43a0b8fd5a2928500110039e43a5eed8480b918967083ea48dc3ab9f13c4a7fb", size = 18638, upload-time = "2025-03-13T13:49:21.846Z" },
 ]
 
-[[package]]
-name = "tiktoken"
-version = "0.13.0"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "regex" },
-    { name = "requests" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/e4/e5/5f3cb2159769d0f4324c0e9e87f9de3c4b1cd45848a96b2eb3566ad5ca77/tiktoken-0.13.0.tar.gz", hash = "sha256:c9435714c3a84c2319499de9a300c0e604449dd0799ff246458b3bb6a7f433c1", size = 38986, upload-time = "2026-05-15T04:51:27.153Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/85/8e/144bde4e01df66b34bb865557c7cd754ed08b036217ebd79c9db5e9048a9/tiktoken-0.13.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:32ac870a806cfb260a02d0cb70426aef02e038297f8ad50df5040bb5af360791", size = 1034888, upload-time = "2026-05-15T04:50:31.579Z" },
-    { url = "https://files.pythonhosted.org/packages/36/18/d4ac9d20956cdebca04841316660ed584c2fecdc2b81722a28bc7ad3b1e4/tiktoken-0.13.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:4d9980f11429ed2d737c463bb1fb78cf330caa026adf002f714aced7849a687b", size = 982970, upload-time = "2026-05-15T04:50:32.961Z" },
-    { url = "https://files.pythonhosted.org/packages/74/ed/6bb8d05b9f731f749fee5c6f5ca63e981143c826a5985877330507bd13b7/tiktoken-0.13.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:3f277ebea5edd7b8bf03c6f9431e1d67d517530115572b2dc1d465326e8f88c7", size = 1115741, upload-time = "2026-05-15T04:50:34.475Z" },
-    { url = "https://files.pythonhosted.org/packages/34/de/2ca96b07a82d972b74fe4b46de055b79c904e45c7eab699354a0bfa697dc/tiktoken-0.13.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:a116178fa7e1b4065bff05214360373a65cac22f965be7b3f73d00a0dbfe7649", size = 1136523, upload-time = "2026-05-15T04:50:35.782Z" },
-    { url = "https://files.pythonhosted.org/packages/ee/dc/9dafec002c2d4424378563cf4cf5c7fb93631d2a55013c8b87554ee4012c/tiktoken-0.13.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:2c397ddda233208345b01bd30f2fca79ff730e55731d0108a603f9bc57f6af3b", size = 1181954, upload-time = "2026-05-15T04:50:36.99Z" },
-    { url = "https://files.pythonhosted.org/packages/a1/d0/1f8578c45b2f24759b46f0b50d31878c63c73e6bf0f2227e10ec5c5408dc/tiktoken-0.13.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:95097e4f89b06403976e498abf61a0ee73a7497e73fb599cb211d8197a054d91", size = 1240069, upload-time = "2026-05-15T04:50:38.221Z" },
-    { url = "https://files.pythonhosted.org/packages/aa/90/28d7f154888610aa9237e541986beb62b479df29d193a5a0617dbb1514d0/tiktoken-0.13.0-cp312-cp312-win_amd64.whl", hash = "sha256:8f2d16e7a7c783ad81f36e457d046d1f1c8af70b22aec8a13238efe531977c41", size = 874748, upload-time = "2026-05-15T04:50:39.587Z" },
-    { url = "https://files.pythonhosted.org/packages/9c/83/b096c859c2a47c11731bf2f5885f4028b809dfe2396582883eed9cae372f/tiktoken-0.13.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:5df5d1507bd245f1ccad4a074698240021239e455eb0bb4ced4e3d7181872154", size = 1034228, upload-time = "2026-05-15T04:50:40.988Z" },
-    { url = "https://files.pythonhosted.org/packages/53/61/c68e123b6d753e3fc2751e9b18e732c9d8bf1e1926762e736eee935d931c/tiktoken-0.13.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:8fe806a50664e83a6ffd56cbd1e4f5dcc6cd32a3e7538f70dc38b1a271384545", size = 982978, upload-time = "2026-05-15T04:50:42.195Z" },
-    { url = "https://files.pythonhosted.org/packages/ef/8b/96cc178cc584e65d363134500f297790b06cd48cdeb1e8fcf7bbe60f4715/tiktoken-0.13.0-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:125bc05005e747f993a83dc67934249932d6e4209854452cd4c0b1d53fba3ba2", size = 1116355, upload-time = "2026-05-15T04:50:43.564Z" },
-    { url = "https://files.pythonhosted.org/packages/86/f5/bab735d2c72ea55404b295d02d092644eb5f7cc6205e34d35eb9abfb9ab2/tiktoken-0.13.0-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:5e6358911cab4adee6712da27d65573496a4f68cf8a2b5fca6a4ad10fc5748cf", size = 1135772, upload-time = "2026-05-15T04:50:44.782Z" },
-    { url = "https://files.pythonhosted.org/packages/4e/b9/6de04ebdf904edfaad87788011b3735087a0c9ea671b9027e1e4e965e8c8/tiktoken-0.13.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:975cbd78d085d75d26b59660e262736dcaed1e35f8f142cd6291025c01d25486", size = 1182415, upload-time = "2026-05-15T04:50:46.422Z" },
-    { url = "https://files.pythonhosted.org/packages/0d/9c/470a05f3b1caf038f44880e334d47ab674e0c80d514c66b375d14d5afa10/tiktoken-0.13.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:75ab9bc99fa020a4c283424590ecd7f3afd70c1c281cb3fa3192a6c3af9f9615", size = 1239879, upload-time = "2026-05-15T04:50:48.052Z" },
-    { url = "https://files.pythonhosted.org/packages/42/a6/c1936d16055436cb32e6c6128d68629622e00f4768562f55653752d34768/tiktoken-0.13.0-cp313-cp313-win_amd64.whl", hash = "sha256:6b1615f0ff71953d19729ceb18865429c185b0a23c5353f1bbca34a394bf60f7", size = 874829, upload-time = "2026-05-15T04:50:49.202Z" },
-    { url = "https://files.pythonhosted.org/packages/d6/07/acb5992c3772b5a36284f742cfb7a5895aa4471d1848ac31464ad50d7fdf/tiktoken-0.13.0-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:6eb4a5bfbc6426938026b1a334e898ac53541360d62d8c689870160cc80abd67", size = 1033600, upload-time = "2026-05-15T04:50:50.4Z" },
-    { url = "https://files.pythonhosted.org/packages/14/e9/742e9aec30f59b9f161f7ff7cd072e02ea836c9e1c0854a8076dfcd40d5c/tiktoken-0.13.0-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:43cee3e5400573b2046fbf092cc7a5bc30164f9e4c95ce20714da929df48737a", size = 982516, upload-time = "2026-05-15T04:50:52.03Z" },
-    { url = "https://files.pythonhosted.org/packages/72/74/ca1541b053e7648254d2e4b42a253e1bb4359f2c91a0a8d49228c794e1a0/tiktoken-0.13.0-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:7de52e3f566d19b3b11bd37eea552c6c305ad74081f736882bd44d148ed4c48d", size = 1115518, upload-time = "2026-05-15T04:50:53.543Z" },
-    { url = "https://files.pythonhosted.org/packages/46/e3/93825eaf5a4a504795b787e5d5dea07fbeb3dabf97aa7b450be8bde59c89/tiktoken-0.13.0-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:51384448aa508e4df84c0f7c1dc3211c7f7b8096325660ee5fc82f3e11b381ce", size = 1136867, upload-time = "2026-05-15T04:50:55.191Z" },
-    { url = "https://files.pythonhosted.org/packages/8c/46/002b68de6827091d5ae90b048f326e8aad8d953520950e5ce1508879414f/tiktoken-0.13.0-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:e28157350f7ebf35008dd8e9e0fdb621f976e4230c881099c85e8cf07eaa50e2", size = 1181826, upload-time = "2026-05-15T04:50:56.296Z" },
-    { url = "https://files.pythonhosted.org/packages/db/c6/d393e3185a276505182f7abd93fe714f3c444a2be9180798fa052347504e/tiktoken-0.13.0-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:165cf1820ea4a354985c2490a5205d4cc74661c934aca79dd0368232fff94e0f", size = 1239489, upload-time = "2026-05-15T04:50:57.918Z" },
-    { url = "https://files.pythonhosted.org/packages/b7/4d/bc07d1f1635d4897a202acc0ae11c2886eaa7325c359ba4741b47bf8e225/tiktoken-0.13.0-cp313-cp313t-win_amd64.whl", hash = "sha256:6c43a675ca14f6f2749ba7f12075d37456015a24b859f2517b9beb4ef30807ec", size = 873820, upload-time = "2026-05-15T04:50:59.528Z" },
-    { url = "https://files.pythonhosted.org/packages/8c/93/0dd6adca026a616c3a92974566b43381eea4b475ce1f36c062b8271a9ac5/tiktoken-0.13.0-cp314-cp314-macosx_10_13_x86_64.whl", hash = "sha256:eaaaef47c2406277181d2086484c317bf7fc433e2d5d03ff94f56b0dcec87471", size = 1034977, upload-time = "2026-05-15T04:51:00.957Z" },
-    { url = "https://files.pythonhosted.org/packages/d9/77/5ec6e6bc5b30bed6d93f7f2162d8f6b32437b3ba27cb527cfe004f6109c9/tiktoken-0.13.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:ca8b310bd93b3772cb1b7922d915446864860f562bdfe4825c63a0aed3fb28cd", size = 983635, upload-time = "2026-05-15T04:51:02.629Z" },
-    { url = "https://files.pythonhosted.org/packages/94/b0/c8ae9aff00d625c50659b4513e707a0462c4bf5d4d6cc1b802103225c02e/tiktoken-0.13.0-cp314-cp314-manylinux_2_28_aarch64.whl", hash = "sha256:32e0c12305105002c047b3bb1070b0dd9a73b0cb3b2856a8972b810e7a4f5881", size = 1116036, upload-time = "2026-05-15T04:51:04.082Z" },
-    { url = "https://files.pythonhosted.org/packages/1b/ac/6a5dddd1d0a6018ecb389bd0353e6b4a515eb4d2286611bd0ace1937b9e1/tiktoken-0.13.0-cp314-cp314-manylinux_2_28_x86_64.whl", hash = "sha256:5ba5fd62507a932d1241346179e3b39bc7bf7408f03c272652d93b3bedf5db24", size = 1135544, upload-time = "2026-05-15T04:51:05.229Z" },
-    { url = "https://files.pythonhosted.org/packages/f4/b8/585032b4384b2f7dcdaddcb52865c83a701a420d09e3c2b4a2be1c450c57/tiktoken-0.13.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:d108bc2d470fc53c8ecd24f2c0fd2b5f98c33e87cdb6aa2e9b8c5dced703d273", size = 1182217, upload-time = "2026-05-15T04:51:06.517Z" },
-    { url = "https://files.pythonhosted.org/packages/cd/b6/993ff1ded3958215fd341a847b8e5ffeb5de473f435296870d314fc91ac4/tiktoken-0.13.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:cb99cb5127449f58d0a2d5f5ccfb390d8dbdfd919c221246caaee29d8725ed51", size = 1239404, upload-time = "2026-05-15T04:51:07.843Z" },
-    { url = "https://files.pythonhosted.org/packages/dd/3d/fef7e06e3b33e7538db0ced734cf9fe23b6832d2ac4990c119c377aec55e/tiktoken-0.13.0-cp314-cp314-win_amd64.whl", hash = "sha256:115c4f26ffa11caac8b54eea35c2ad38c612c20a48d35dd15d70a02ac6f51f58", size = 918686, upload-time = "2026-05-15T04:51:08.925Z" },
-    { url = "https://files.pythonhosted.org/packages/c1/82/a7fc44582bc32ab00de988a2299bf77c077f59068b233109e34b7d6ca7e6/tiktoken-0.13.0-cp314-cp314t-macosx_10_13_x86_64.whl", hash = "sha256:472527e9132952f2fbf77cd290658bacf003d4d5a3fabc18e5fbd407cbae4d9b", size = 1034454, upload-time = "2026-05-15T04:51:10.035Z" },
-    { url = "https://files.pythonhosted.org/packages/37/d0/24d8a890c14f432a05cea669c17bebeaa99f96a7c79523b590f564246411/tiktoken-0.13.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:4e2f67d27c9626cdd25fe33d9313c5cdb3d8d82da646b68d6eb8e7e9c20e6448", size = 982976, upload-time = "2026-05-15T04:51:11.23Z" },
-    { url = "https://files.pythonhosted.org/packages/49/b7/2ab43f62788a9266187a9bfc1d3af99ad83e5eaa25fbef168a69cd5ad14f/tiktoken-0.13.0-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:2b920b35805cd64585a37c3dc7ce65fba4d2d36016be01e1d7942482ca29093a", size = 1115526, upload-time = "2026-05-15T04:51:12.608Z" },
-    { url = "https://files.pythonhosted.org/packages/64/39/1494321ed323ce7a14d88e3cd6cb9058625977df1c6961ddc492bd10a9f3/tiktoken-0.13.0-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:493af3aa28a4aaf2e3d2600a2ee717252c9bf5ab38fff94eb5a02db5ab77e5ad", size = 1136466, upload-time = "2026-05-15T04:51:13.926Z" },
-    { url = "https://files.pythonhosted.org/packages/96/d9/dfd086aa2d918c563a140720e0ce296cada1634efd2783d5cf51e05f984e/tiktoken-0.13.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:6644c9c2b5cf3916f5a3641d7d12fdb3f006a7b3d9ff6acdaec44e29ab1ff91e", size = 1181863, upload-time = "2026-05-15T04:51:15.025Z" },
-    { url = "https://files.pythonhosted.org/packages/2f/68/a18b4f307086954fdae32714cb4f85562e34f9d34ab206e61f1816aa6018/tiktoken-0.13.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:5cb65b60b9408563676d874a3a4ee573370066f0dc4e29d84e82e989c6517424", size = 1239218, upload-time = "2026-05-15T04:51:16.103Z" },
-    { url = "https://files.pythonhosted.org/packages/16/5b/f2aa703a4fc5d2dff73460a7d46cc2f3f44aa0f3dd8eeb20d2a0ecf68862/tiktoken-0.13.0-cp314-cp314t-win_amd64.whl", hash = "sha256:85b78cc3a2c3d48723ca751fa981f1fedccd54194ca0471b957364353a898b07", size = 918110, upload-time = "2026-05-15T04:51:17.237Z" },
-]
-
 [[package]]
 name = "tokenizers"
 version = "0.22.2"
@@ -3108,41 +2848,64 @@ wheels = [
 name = "torch"
 version = "2.14.0"
 source = { registry = "https://pypi.org/simple" }
+resolution-markers = [
+    "sys_platform != 'linux'",
+]
 dependencies = [
-    { name = "cuda-bindings", marker = "python_full_version < '3.15' and sys_platform == 'linux'" },
-    { name = "cuda-toolkit", extra = ["cublas", "cudart", "cufft", "cufile", "cupti", "curand", "cusolver", "cusparse", "nvjitlink", "nvrtc", "nvtx"], marker = "sys_platform == 'linux'" },
-    { name = "filelock" },
-    { name = "fsspec" },
-    { name = "jinja2" },
-    { name = "networkx" },
-    { name = "nvidia-cudnn-cu13", marker = "sys_platform == 'linux'" },
-    { name = "nvidia-cusparselt-cu13", marker = "sys_platform == 'linux'" },
-    { name = "nvidia-nccl-cu13", marker = "sys_platform == 'linux'" },
-    { name = "nvidia-nvshmem-cu13", marker = "sys_platform == 'linux'" },
-    { name = "setuptools" },
-    { name = "sympy" },
-    { name = "triton", marker = "python_full_version < '3.15' and sys_platform == 'linux'" },
-    { name = "typing-extensions" },
+    { name = "filelock", marker = "sys_platform != 'linux'" },
+    { name = "fsspec", marker = "sys_platform != 'linux'" },
+    { name = "jinja2", marker = "sys_platform != 'linux'" },
+    { name = "networkx", marker = "sys_platform != 'linux'" },
+    { name = "setuptools", marker = "sys_platform != 'linux'" },
+    { name = "sympy", marker = "sys_platform != 'linux'" },
+    { name = "typing-extensions", marker = "sys_platform != 'linux'" },
 ]
 wheels = [
     { url = "https://files.pythonhosted.org/packages/17/76/bb4770f56cf6d8971671dbcbb7493e5a6a15ad2825f4e359b02c27c38297/torch-2.14.0-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:c1f844f1c750e87df4b68bc3afbc0e2b0c7ef19d7b8f666e48bdcf6a0c4f0056", size = 127303200, upload-time = "2026-09-02T13:43:20.311Z" },
-    { url = "https://files.pythonhosted.org/packages/fe/7b/ec44bacf2c8886b85ba4ca2285e8b09f2dff5d9c99e6a031326954082cb5/torch-2.14.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:ada340e62591d06a2bcc2d68170f20f45f0b0665d372dc510a8ed7eb3b1d609a", size = 454010251, upload-time = "2026-09-02T13:44:24.927Z" },
-    { url = "https://files.pythonhosted.org/packages/15/71/49399acd41f750a906c686bd23c08a2001ccb8dd25f2971003c2ed89c1dd/torch-2.14.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:fecffb58f51fd643d213acd68da21cc3fc19bea05a3bc64b4ee55128f47a4963", size = 554620488, upload-time = "2026-09-02T13:44:49.442Z" },
     { url = "https://files.pythonhosted.org/packages/be/16/9489b137112040f9911d7527e452854f21cc4e499ce0da79864e6a7451a7/torch-2.14.0-cp312-cp312-win_amd64.whl", hash = "sha256:cad84f41bbdf3dcf333ce394aeeaf25237c4d94fd6b659ba5eb813c829978823", size = 124114011, upload-time = "2026-09-02T13:43:55.034Z" },
     { url = "https://files.pythonhosted.org/packages/ca/40/0db773452c2a62b37761d3f418acf933d381f9e87077036fb57c2a386c37/torch-2.14.0-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:9d4b1022a5d9b71282ec67ad0d9e7235870096b8a246dc1c32d6ea1fc83dc998", size = 127311393, upload-time = "2026-09-02T13:43:59.607Z" },
-    { url = "https://files.pythonhosted.org/packages/13/36/537fd9da2adad49e7b2bb20741398625bee548493158274e87369a8eed56/torch-2.14.0-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:731b9ebdea402b8b1996d4c2ae613b16660e559b19e47bdc45d970568bc91c53", size = 454010525, upload-time = "2026-09-02T13:45:03.719Z" },
-    { url = "https://files.pythonhosted.org/packages/21/f1/39bd13b21f57d1982b7f3ddf663f01c7266e2957714880744eba9e8c8d11/torch-2.14.0-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:84bf384779a10c02fc3c6bdbab71a9cb66b0dd93c652d1ed5d6dfc0cb37e5962", size = 554619993, upload-time = "2026-09-02T13:45:28.209Z" },
     { url = "https://files.pythonhosted.org/packages/89/a8/683d9c44737554b67ca76dd2db4f42258a0f014246cb511293e51e0154bd/torch-2.14.0-cp313-cp313-win_amd64.whl", hash = "sha256:0e7cf18cb0d8bd666b6120932e29c7aef3502b61a08b44da4839580c539a7cdb", size = 124113865, upload-time = "2026-09-02T13:44:33.705Z" },
     { url = "https://files.pythonhosted.org/packages/ee/90/1241e7db5ccc2455f8735bd6b1becfad39916206ad18001c4c0014d139e2/torch-2.14.0-cp314-cp314-macosx_14_0_arm64.whl", hash = "sha256:860423e970f2ce02c4476e8e2d1350131b1c5c5a5e4912180e78b50b53241efa", size = 127321431, upload-time = "2026-09-02T13:44:38.236Z" },
-    { url = "https://files.pythonhosted.org/packages/68/f0/bbeba65e3fbb4b8f61ea19cf4ebea9f4268cc6fe64e6f7d38bfb6cc152eb/torch-2.14.0-cp314-cp314-manylinux_2_28_aarch64.whl", hash = "sha256:b985c7defeb8d28691b7513ebaecc64946c5f68ec770e9f4ddba39688864f46a", size = 454027631, upload-time = "2026-09-02T13:45:43.73Z" },
-    { url = "https://files.pythonhosted.org/packages/50/75/8d2b9a7e724759470c209489b79260cac537f091cc9aac8001c8d2bc845c/torch-2.14.0-cp314-cp314-manylinux_2_28_x86_64.whl", hash = "sha256:b2cd92bce63d40bf6fc2e5d840fc2f0063bd180a242daa761cb6088cc2f46e27", size = 554623549, upload-time = "2026-09-02T13:46:04.252Z" },
     { url = "https://files.pythonhosted.org/packages/9a/1e/a5475c00b0555e686333e6b4036f2213e7cbea021a772ce6f9ced4dcbd2f/torch-2.14.0-cp314-cp314-win_amd64.whl", hash = "sha256:44b044b9f6f633d982839422a57433d6a1da520037fd88e0c8a47efde589b3b8", size = 124110863, upload-time = "2026-09-02T13:45:12.764Z" },
     { url = "https://files.pythonhosted.org/packages/a5/49/bbaee76337742a42d2c5b0296ea62252567050e1d821bc2283b2e72ba6fb/torch-2.14.0-cp314-cp314t-macosx_14_0_arm64.whl", hash = "sha256:553aec938d37d77b783bcf801e638cad068870e7643c47eadac21eb180f551ed", size = 127653463, upload-time = "2026-09-02T13:45:17.1Z" },
-    { url = "https://files.pythonhosted.org/packages/92/b5/6cc7a511bab384fbe8f4b8ddeecdd22e724b2162d6f15076f07a0a7ef15b/torch-2.14.0-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:cd8cd8f714d511ccdca907282d1da3d9be8322d4e1520b9c3bce39a5c1318a4b", size = 454009927, upload-time = "2026-09-02T13:46:19.637Z" },
-    { url = "https://files.pythonhosted.org/packages/b6/da/0f04fe15fd05bf3f613a359b14acb44c35ae06fe69da0aefa8b5cdb4f9f9/torch-2.14.0-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:d2526f71e6638133b97b3cd2881ece3df521460a4727030e8ae2a72a7d3ae31d", size = 554580530, upload-time = "2026-09-02T13:46:34.818Z" },
     { url = "https://files.pythonhosted.org/packages/f8/c3/72ae1f02747b1f012e1975743e48cd608f83095d7f9ce58de78b79248b35/torch-2.14.0-cp314-cp314t-win_amd64.whl", hash = "sha256:731784e3914843c6bcc7aba3987ff7610ac57dbbc816a5d6b9b62e04c240a641", size = 124400194, upload-time = "2026-09-02T13:45:53.555Z" },
 ]
 
+[[package]]
+name = "torch"
+version = "2.14.0+cpu"
+source = { registry = "https://download.pytorch.org/whl/cpu" }
+resolution-markers = [
+    "sys_platform == 'linux'",
+]
+dependencies = [
+    { name = "filelock", marker = "sys_platform == 'linux'" },
+    { name = "fsspec", marker = "sys_platform == 'linux'" },
+    { name = "jinja2", marker = "sys_platform == 'linux'" },
+    { name = "networkx", marker = "sys_platform == 'linux'" },
+    { name = "setuptools", marker = "sys_platform == 'linux'" },
+    { name = "sympy", marker = "sys_platform == 'linux'" },
+    { name = "typing-extensions", marker = "sys_platform == 'linux'" },
+]
+wheels = [
+    { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.14.0%2Bcpu-cp312-cp312-linux_s390x.whl", hash = "sha256:07aefe1a437b6f1b41b0cba15e16583e2f43549ec9d062fcea8e7981a78e014a", upload-time = "2026-09-02T18:31:32Z" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.14.0%2Bcpu-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:da8140c3d4a41500d29710e35bf8e66a4295ec31026487c69f54a3f583310f8d", upload-time = "2026-09-02T18:31:37Z" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.14.0%2Bcpu-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:a09987c95ec4cffdb6df798d3d641558110a334cfccce22f2f046d83142bc260", upload-time = "2026-09-02T18:31:42Z" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.14.0%2Bcpu-cp313-cp313-linux_s390x.whl", hash = "sha256:d87cfff3af33c937b88c9bc6c0dfa17f2156e2599f63447c696f2345928b518a", upload-time = "2026-09-02T18:31:55Z" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.14.0%2Bcpu-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:092d5c12938850dfbd90a654b3c8dac34c33e300f88eb19ee6f4ef93992c6347", upload-time = "2026-09-02T18:31:59Z" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.14.0%2Bcpu-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:160e1bc46aeded3111d2801f8ae10dc9a1b946843a7e126b4dbf5e19c5706e95", upload-time = "2026-09-02T18:32:05Z" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.14.0%2Bcpu-cp314-cp314-linux_s390x.whl", hash = "sha256:266a253980047f3c037191f45d7e7ecfa838d13102141ca57b86fcc892663004", upload-time = "2026-09-02T18:32:17Z" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.14.0%2Bcpu-cp314-cp314-manylinux_2_28_aarch64.whl", hash = "sha256:27b34640fea7268862961b734c723873e15b1c2657b1eb84bcfac053e5841527", upload-time = "2026-09-02T18:32:23Z" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.14.0%2Bcpu-cp314-cp314-manylinux_2_28_x86_64.whl", hash = "sha256:f152f41dc5dc462afe0de780e451ebb47ea8b4451f8f919f9537aa8e2cbe1d7e", upload-time = "2026-09-02T18:32:29Z" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.14.0%2Bcpu-cp314-cp314t-linux_s390x.whl", hash = "sha256:c1d81be03f715eca5b065fc767f73b2a26668a16d614e163a4378a3f38a5e471", upload-time = "2026-09-02T18:32:39Z" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.14.0%2Bcpu-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:a6ff46c0c0c4f5b9b399dff5e4856a98ce18e61ca14ad74b21790174c7cbde08", upload-time = "2026-09-02T18:32:43Z" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.14.0%2Bcpu-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:2baf9cbaef964d821465df0c53a91cc01b2d0ea29ebd199e2f9c7d27a7fc70a4", upload-time = "2026-09-02T18:32:48Z" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.14.0%2Bcpu-cp315-cp315-manylinux_2_28_aarch64.whl", hash = "sha256:07d50e40232d2757be323693e38f531e04ee654d40537bc0b04e787c1e73a27a", upload-time = "2026-09-02T18:32:57Z" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.14.0%2Bcpu-cp315-cp315-manylinux_2_28_x86_64.whl", hash = "sha256:a8b2fa9a03d81bc083f279737fce1cd8d1ed2e267da92215260cd644dcfdd3fe", upload-time = "2026-09-02T18:33:02Z" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.14.0%2Bcpu-cp315-cp315t-manylinux_2_28_aarch64.whl", hash = "sha256:e22ddf8a9fff9934fe2dd2440d45c437bb0539f2d6d24b57b26981d6dca4157c", upload-time = "2026-09-02T18:33:11Z" },
+    { url = "https://download-r2.pytorch.org/whl/cpu/torch-2.14.0%2Bcpu-cp315-cp315t-manylinux_2_28_x86_64.whl", hash = "sha256:18b417c953e9b4d8b79294ca5184586790f0a609b3929e39258cea854b945870", upload-time = "2026-09-02T18:33:16Z" },
+]
+
 [[package]]
 name = "tornado"
 version = "6.5.8"
@@ -3201,21 +2964,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/df/56/bbd60dd8668055803bf8ba55a81f9b8a8b31497f620109a9671d26a2076d/transformers-5.12.1-py3-none-any.whl", hash = "sha256:2a5e109d2021265df7098ffbb738295acaf5ad256f12cbc586db2ea4dcbb1a8a", size = 11150587, upload-time = "2026-06-15T17:27:46.679Z" },
 ]
 
-[[package]]
-name = "triton"
-version = "3.8.0"
-source = { registry = "https://pypi.org/simple" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/87/07/0f8cd8e8db0472334253efdaaab3d0819fea27aa99bf0e7f1aeea4ceb5ae/triton-3.8.0-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:a9c404c69ed4a39e8ec632eaf6b9fe058a060bf98979c177f6ef666f06bb8d50", size = 226474486, upload-time = "2026-08-28T16:08:18.29Z" },
-    { url = "https://files.pythonhosted.org/packages/c1/09/b7012e5bfae67640f268aa584caa80fe1674f6b0da949046b679972c33e3/triton-3.8.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:e91ffa46d095b252248297292dd22bcbacd53a125a0c2eefbbbf74925a320bc3", size = 247972921, upload-time = "2026-08-28T15:55:53.157Z" },
-    { url = "https://files.pythonhosted.org/packages/87/4d/4c564374bcdadb166fccbf3e45aee0d4a473f88d341761bd2fefe3b8e8c1/triton-3.8.0-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b7004666652f500ed854a86988e4b3d69d247188b5d2092b5df1e44f4a954099", size = 226476793, upload-time = "2026-08-28T16:08:30.956Z" },
-    { url = "https://files.pythonhosted.org/packages/b0/b6/3394d5548404c1cabd1dadadd28d0b3f9478db1dff8180da53bb3f0a1e19/triton-3.8.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:1f0497218e26b7d79773ad9c2a3fa3b539ee69f587a13fac2e552b1d322a8015", size = 247975122, upload-time = "2026-08-28T15:56:04.112Z" },
-    { url = "https://files.pythonhosted.org/packages/b8/59/bf0e9493118bb353ab59a5d6a65db3618d9b314417cc1459f0121e0ec5c9/triton-3.8.0-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:1f6b48d0591929a3867973acac3dccd4e058585f91bfb41022de496c9ffab304", size = 226488654, upload-time = "2026-08-28T16:08:47.141Z" },
-    { url = "https://files.pythonhosted.org/packages/93/d9/08c75f3459f19ad00425b564058e40efa4bcd79b816064cf27499303ea42/triton-3.8.0-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:387dae4cb0089a7b6ba1a428ae0782b65c4c58f57d94617cb22ca8593d8ccbca", size = 247972313, upload-time = "2026-08-28T15:56:14.007Z" },
-    { url = "https://files.pythonhosted.org/packages/7c/34/429c5592181cfb7361a0a8e0bff218e7224b726709d75da2472b3e819f70/triton-3.8.0-cp314-cp314t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:1b84e7d512490ba529111260fa6f7cad8b254a6bb5fbdf41d5ef9a5e57f52d0a", size = 226591133, upload-time = "2026-08-28T16:09:02.271Z" },
-    { url = "https://files.pythonhosted.org/packages/fe/d1/aa8a3e935c37efee7945984fdb64d7e0851bf6d920afd97b2d21f9d23360/triton-3.8.0-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:74217bb56ed8692759227758e4c4b3bd2d608a209c1a7a081bf361fb4c2c1bf9", size = 248077577, upload-time = "2026-08-28T15:56:24.94Z" },
-]
-
 [[package]]
 name = "truststore"
 version = "0.10.4"