[7/8] specdec-release: add A|B benchmark validity gate and greedy-match report by Zhehao-Hu · Pull Request #2935 · NVIDIA/Model-Optimizer

Zhehao-Hu · 2026-10-22T04:30:46Z

[7/8] Day-0 speculative-decoding readiness flow. Merge in order 1 → 8. Base: [6/8] #2934. Reads compare_ab.py's ab_summary.json from [5/8].
Series: [1/8] #2839 · [2/8] #2930 · [3/8] #2931 · [4/8] #2932 · [5/8] #2933 · [6/8] #2934 · [7/8] #2935 (this) · [8/8] #2936

What does this PR do?

Type of change: New feature

Adds the specdec-release benchmark gates. They use the same contract as [6/8]: stdlib-only, JSON verdict, exit 0/1/2.

scripts/gate_bench.py decides whether a compare_ab.py summary is a valid matched measurement. It doesn't decide whether the numbers are good enough.

Every submitted concurrency and repeat is present (BENCH_INCOMPLETE).
The arms and rows match: target, engine and version, GPU, parallelism, dataset, output length, temperature and concurrency (ARMS_UNMATCHED).
Speculation is off in arm A, and on in arm B with the submitted algorithm, drafter and token count (SPEC_CONFIG_MISMATCH).
The numbers are plausible (ANOMALOUS): AL and speedup no higher than tokens + 1, positive TPS, paired turns.
AL, speedup and TPS per row are returned as evidence, together with the measurement setup.

scripts/gate_correctness.py is report-only. It returns the greedy exact-match rate between the arms at concurrency 1 (all turns and first turns), over rows with no comparator problems and speculation on in arm B. Next to it, it reports the target-alone control from [5/8] (a_self_match, arm A at concurrency 1 vs the next concurrency) as min_self_* rates, the noise floor; without one it notes that a low rate can't be told apart from target drift. It does not repeat gate_bench's other checks, so read its rates alongside a passing gate_bench. It always passes unless its input is bad.

Usage

python plugins/modelopt/skills/specdec-release/scripts/gate_bench.py \
    --summary <ab>/ab_summary.json --concurrencies 1,8,32 --repeats 1 \
    --algorithm DFLASH --num-spec-tokens 7 \
    --draft /cicd/drafts/Qwen3-8B/dflash2/<run_id> --target /hf-local/Qwen/Qwen3-8B
python plugins/modelopt/skills/specdec-release/scripts/gate_correctness.py --summary <ab>/ab_summary.json

Testing

tests/test_specdec_gates.py gains the bench and correctness cases: each failure class, the pass path, and malformed or partial summaries. Skills suite on this commit: 162 passed, 1 skipped.
GPU artifacts (OCI-JHB): run on the login node against six real ab_summary.json files from 5 drafters (1–2 repeats each). Every summary passed with all rows valid, and exact match came out at 0.956–0.963.

Before your PR is "Ready for review"

Make sure you read and follow Contributor guidelines and your commits are signed (git commit -s -S).

Make sure you read and follow the Security Best Practices (e.g. avoiding hardcoded trust_remote_code=True, torch.load(..., weights_only=False), pickle, etc.).

Is this change backward compatible?: ✅ (new scripts)
If you copied code from any other sources or added a new PIP dependency, did you follow guidance in CONTRIBUTING.md: N/A (stdlib only)
Did you write any new necessary tests?: ✅
Did you update Changelog?: N/A (one entry for the skill in [8/8])
Did you get Claude approval on this PR?: ❌ - not yet run

Additional Information

The gates set no performance bar. Variance runs show AL is stable to < 0.4% CV, but speedup above C=1 varies 2–3% between runs. A throughput threshold therefore needs a repeat policy first, and it belongs to the later release gates.

copy-pr-bot · 2026-10-22T04:30:51Z

Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually.

Contributors can view more details about this message here.

coderabbitai · 2026-10-22T04:30:54Z

Important

Draft PR not reviewed

Draft PRs are not automatically reviewed by default.

Trigger a manual review

To automatically review draft PRs, update your CodeRabbit configuration:

reviews:
  auto_review:
    drafts: true

Autofix · Keep fixing CodeRabbit findings and required CI, and resolving merge conflicts

_{Comment @coderabbitai help to get the list of available commands.}

…strict (#2839) > **[1/8] Day-0 speculative-decoding readiness flow.** Merge in order 1 → 8. Base: `main`. > Series: [1/8] #2839 (this) · [2/8] #2930 · [3/8] #2931 · [4/8] #2932 · [5/8] #2933 · [6/8] #2934 · [7/8] #2935 · [8/8] #2936 ### What does this PR do? Type of change: Bug fix [common/check_regression.py](https://github.com/NVIDIA/Model-Optimizer/blob/main/tools/launcher/common/check_regression.py) gates DFlash-family training runs on final loss and accuracy. Four things stopped that gate from catching a bad run: 1. **It read the wrong checkpoint on long runs.** `find_trainer_state()` sorted `checkpoint-*` as strings, so `checkpoint-8000` ranked after `checkpoint-12000` and an older checkpoint's metrics were checked. Any run whose saved steps differ in digit count was affected; the ~92K-step full DFlash2 recipe in `hf_online_dflash2.yaml` saves every 4000 steps. It now sorts by step number. 2. **An unreadable run passed.** With thresholds set, a missing `trainer_state.json`, or one with no training logs, only warned and exited 0. An empty threshold variable (`MAX_FINAL_LOSS=""`) crashed on `float('')`. 3. **A regression never failed the job.** `dflash_online_training.sh` runs the check as `check_regression.py … || true`, so Slurm reports `COMPLETED` even when the log says `REGRESSION`. The verdict also existed only as log text. 4. **A crashed run was still graded.** The script's `ERR` trap only records a failure, so after a failed `accelerate launch` it went on to export and run the check, and a checkpoint that survived the crash could pass. Changes: - `check_regression.py`: - Sorts checkpoints by step number. - Fails when thresholds are set but there are no metrics to check, including a `trainer_state.json` of the wrong shape. An empty threshold variable counts as unset. A threshold that isn't a finite number (`7,0`, `nan`) fails as `METRICS_MISSING`. - A NaN or infinite value for a metric that has a threshold fails as `TRAIN_REGRESSION`. - Takes `--json <path>` and writes `{pass, failure_class, trainer_state, metrics, thresholds, messages}` as strict JSON (non-finite metrics as `null`). `failure_class` is `null`, `TRAIN_REGRESSION` or `METRICS_MISSING`. The verdict is serialized before the file is opened, so a failure can't leave a truncated file. - Its existing log lines (`=== Regression Check (…) ===`, `PASS:` / `REGRESSION:`, `Regression check PASSED`) are unchanged, so existing log readers keep working. A failure now also prints `Regression check FAILED`. - `dflash_online_training.sh` writes the verdict to `${OUTPUT_DIR}/regression_check.json`, next to the exports. `REGRESSION_STRICT=1` drops the `|| true`, so a regression fails the task through the existing `ERR` trap and `exit_handler`. **The default (`0` or unset) is unchanged (warn only)**, so the other examples with possibly uncalibrated thresholds don't start failing. Any other value fails the task at startup, before installing or training. - `dflash_online_training.sh` also skips export and the check when training fails, still reporting the failure like any `ERR`-trap failure, and removes an old `regression_check.json` first thing, so no early exit can leave an earlier run's verdict behind. - `examples/Qwen/Qwen3-8B/hf_online_dflash2.yaml`: - Sets `REGRESSION_STRICT: "1"`. - Recalibrates `MAX_FINAL_LOSS` from 5.0 to 7.0. The 5.0 was inherited from `hf_online_dflash.yaml`, whose own reference curve only drops below 5.0 at step ~2500 of a 12.5K-step run. DFlash2 adds a selector loss term and this example stops at 2000 steps, so 5.0 fails every healthy run. `MIN_FINAL_ACC` stays at 0.15. - The `speculative-decoding` skill's `dflash.md` and `dflash2.md` describe the new gate: judge a run by `regression_check.json`, the two failure classes, strict mode, and DFlash2's 7.0 threshold. ### Usage ```bash MAX_FINAL_LOSS=7.0 MIN_FINAL_ACC=0.15 \ python3 common/check_regression.py /scratchspace/dflash2_bs16 --json /scratchspace/dflash2_bs16/regression_check.json echo $? # 0 pass, 1 regression or nothing to check ``` ```yaml environment: - MAX_FINAL_LOSS: "7.0" - REGRESSION_STRICT: "1" # fail the training task on a regression ``` ### Testing - `tools/launcher/tests/test_check_regression.py`: 4 new test functions (13 cases). Run against `main`'s `check_regression.py`, 17 of the file's 18 cases fail: - `test_latest_checkpoint_is_chosen_by_step_number` guards the string-sort bug. - `test_empty_threshold_var_is_unset` guards the `float('')` crash. - `test_cli_exit_code_and_json_verdict` is parametrized over a missing `trainer_state.json`, a truncated one, two of the wrong shape, a NaN loss, an unchecked infinite metric, a regression and a pass. Each case checks the exit code and parses the verdict as strict JSON, so it covers the missing-metrics hole and the `--json` contract. - `test_invalid_threshold_writes_failed_verdict` covers `7,0`, `nan` and `inf`. - `tools/launcher/tests/test_dflash_online_training.py` (5 cases) runs the real script in a sandbox: stubbed `pip`, `nvidia-smi`, `accelerate`, exporter and `torch`, a checkpoint, and an old passing verdict. Each case asserts the exact exit code. Against `main`'s script, all 5 fail: - A failing launch leaves no verdict and exits 1; a succeeding one grades the checkpoint and exits 0 with no `ERR`-trap error. - With a checkpoint over the threshold, `REGRESSION_STRICT=1` exits 1 and `0` exits 0, both writing `TRAIN_REGRESSION`. - `REGRESSION_STRICT=true` exits 1 without launching training and leaves no verdict. - Full launcher suite on this commit: `uv run --with pytest python3 -m pytest tests/`, 183 passed. - `dflash_online_training.sh`: `bash -n` passes. - **GPU (OCI-JHB, GB300, global batch 8):** five 2000-step runs of this example with this change passed the strict gate. Final loss was 6.37–6.71 and accuracy 0.167–0.177, against 7.0 / 0.15. The calibration run that motivated 7.0 (before this change) finished at 6.51 / 0.181. The seed-to-seed spread puts the loss margin at about 4%; see the variance note under Additional Information. - Not run: the strict-failure path and a real training crash on GPU (covered by the sandbox test above). ### Before your PR is "*Ready for review*" Make sure you read and follow [Contributor guidelines](https://github.com/NVIDIA/Model-Optimizer/blob/main/CONTRIBUTING.md) and your commits are signed (`git commit -s -S`). Make sure you read and follow the [Security Best Practices](https://github.com/NVIDIA/Model-Optimizer/blob/main/SECURITY.md#security-coding-practices-for-contributors) (e.g. avoiding hardcoded `trust_remote_code=True`, `torch.load(..., weights_only=False)`, `pickle`, etc.). - Is this change backward compatible?: ✅ (strict mode is opt-in; log output unchanged) - If you copied code from any other sources or added a new PIP dependency, did you follow guidance in `CONTRIBUTING.md`: N/A - Did you write any new necessary tests?: ✅ - Did you update [Changelog](https://github.com/NVIDIA/Model-Optimizer/blob/main/CHANGELOG.rst)?: N/A - Did you get Claude approval on this PR?: ❌ - not yet run ### Additional Information - Part of the Day-0 speculative-decoding workflow: the `specdec-release` skill ([8/8]) gates training on `regression_check.json`, so it needs a verdict it can read and a job state that reflects it. - **Why not reuse `day0-release/scripts/gate_run.py`?** The two sit at different layers and check different things, so their schemas stay independent on purpose: - `gate_run.py` is an agent-side gate for an *evaluation* run. It reads a run summary the agent builds from NEL output, and checks per-task status, sample counts and judge errors. None of that exists for a training run. - `check_regression.py` runs *inside* the Slurm training task, on rank 0, and its verdict decides the task's exit status in strict mode. It reads `trainer_state.json` against thresholds from the launcher YAML, and has to work for launcher users who never load a skill. A launcher script importing a skill script would also invert the dependency: skills drive the launcher, not the other way round. - The skill-side counterpart of `gate_run.py` for training is `specdec-release/scripts/gate_train.py` ([6/8] #2934). It reads `regression_check.json` and returns the day-0 gate shape (`{pass, failure_class, detail, …}`), with `failure_class` from the shared triage vocabulary. That is the adapter layer, so `check_regression.py` doesn't need to match `gate_run.py`. - What the two share is the convention: a boolean `pass`, and a `failure_class` that is `null` on a pass. The launcher emits only `METRICS_MISSING` and `TRAIN_REGRESSION`, and `gate_train.py` treats any other value as `TRAIN_REGRESSION`, so the launcher can add detail fields without breaking the gate. - Other Qwen3-8B examples share the inherited `MAX_FINAL_LOSS: "5.0"` (`hf_online_domino.yaml`, `hf_online_lilicorr.yaml`). They are left unchanged and non-strict because there is no calibration run for them. - Variance: a seed-1 retrain landed at loss 6.705, 4.2% under the 7.0 floor. Accuracy has more headroom (11%). Recalibrating from more seeds is planned for the release gates, not this PR.   ## Summary by CodeRabbit * **New Features** * Training runs with an output directory now produce a regression-check verdict file reporting whether configured quality thresholds passed. * Regression checks account for missing or invalid metrics and select checkpoints by numeric step. * **Bug Fixes** * Failed training no longer proceeds to checkpoint export or regression checks. * Strict mode fails the task when regression checks fail; invalid strict-mode values stop the run before training starts. * **Documentation** * Updated DFlash2 guidance and example settings for the final-loss threshold and strict-mode behavior.  --------- Signed-off-by: Zhehao Hu <zhehaoh@nvidia.com> Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>

- gate_bench.py: decides whether a compare_ab.py summary is a valid matched measurement: every submitted concurrency and repeat present, arms and rows matched (target, engine, GPU, parallelism, dataset, length, temperature, concurrency), speculation off in arm A and on in arm B with the submitted algorithm, drafter and token count, and plausible numbers. AL, speedup and TPS are returned as evidence with the measurement setup. - gate_correctness.py: report-only greedy exact-match rate between the arms at concurrency 1, over rows with no comparator problems and speculation on in arm B. It does not repeat gate_bench's other checks. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Signed-off-by: Zhehao Hu <zhehaoh@nvidia.com>

gate_correctness reports compare_ab's a_self_match (arm A at concurrency 1 vs the next concurrency) as min_self_exact_match_rate and min_self_first_turn_exact_match_rate, and in its detail. Without a control it adds a note that a low rate cannot be told apart from the target's own batch-shape drift. Still report-only. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Signed-off-by: Zhehao Hu <zhehaoh@nvidia.com>

…ction (#2930) > **[2/8] Day-0 speculative-decoding readiness flow.** Merge in order 1 → 8. Base: `main` ([1/8] has merged). > Series: [1/8] #2839 (merged) · [2/8] #2930 (this) · [3/8] #2931 · [4/8] #2932 · [5/8] #2933 · [6/8] #2934 · [7/8] #2935 · [8/8] #2936 ### What does this PR do? Type of change: Bug fix The vLLM smoke test (`common/specdec/vllm_smoke_test.sh`) is the serving check after draft training. It had six problems: 1. **It could serve the wrong checkpoint.** `ar_eval_mtbench.sh` and `vllm_smoke_test.sh` picked the newest checkpoint by sorting on a dash-separated field of the **whole path**, so a dash in a parent directory (e.g. `/data/my-drafts/...`) picked the wrong one. `quantize_drafter.sh` had a third, different sort. The smoke test also ignored `exported-checkpoint-final`. 2. **Every throughput figure printed `?`.** Timing used `bc`, which the vLLM image doesn't have. 3. **A drafter that never speculated passed.** With `MIN_ACCEPTANCE_LENGTH` set, a vLLM log with no acceptance length only warned. 4. **The acceptance length covered only the last few seconds.** It came from the log's "Mean acceptance length" line, which covers only vLLM's last logging interval. 5. **The verdict existed only as log text.** 6. **The server wait was fixed at 180 s.** Qwen3.8-27B with a DFlash2 drafter takes longer to start on GB300 (torch.compile, kernel JIT, CUDA graph capture, GDN warmups), so every smoke attempt stopped at `server_timeout`. The script's exit then tore the container down mid-warmup, and the engine's next exec failed with a ptxas ENOENT that read like the cause. Changes: - `service_utils.sh`: new `latest_checkpoint <dir> <prefix>`. It returns `<dir>/<prefix>final` if present, else the highest numeric step, keyed on the directory's own name. It replaces the three ad hoc sorts in `ar_eval_mtbench.sh`, `vllm_smoke_test.sh` and `quantize_drafter.sh`. - `vllm_smoke_test.sh`: - Prefers `exported-checkpoint-final`, as `quantize_drafter.sh` already did. - Times prompts with shell arithmetic and `python3` instead of `bc`. - Computes the mean acceptance length over the whole run from vLLM's cumulative `/metrics` counters: 1 + `spec_decode_num_accepted_tokens_total` / `spec_decode_num_drafts_total`. - With `MIN_ACCEPTANCE_LENGTH` set, fails when no speculative drafts were recorded. - Fails loudly if `service_utils.sh` is missing (it used to be optional, so the failure surfaced as a misleading `draft_missing`). Only a missing file is fatal: `source` returns the status of the file's last command, a rank-0 append that fails outside a launcher working directory. - `SERVER_TIMEOUT` sets the server wait in seconds (default 180) and appears in the timeout reason. - Checks `MIN_ACCEPTANCE_LENGTH` (a finite number), and `NUM_SPEC_TOKENS` and `SERVER_TIMEOUT` (positive integers without leading zeros, since `NUM_SPEC_TOKENS` goes into vLLM's JSON config), before any work, and fails with `stage: invalid_config` and a reason naming the value. Both checks run after the `EXIT` trap is set, so even these failures replace any earlier `SMOKE_JSON`. - Optional `SMOKE_JSON=<path>` writes the verdict on every exit: `{stage, pass, reason, method, target, draft, num_speculative_tokens, prompts passed/failed, tokens, average tok/s, mean_acceptance_length, min_acceptance_length}`. `stage` says how far it got (`invalid_config`, `starting`, `draft_missing`, `server_died`, `server_timeout`, `serving`, `completed`), so a downstream gate can tell "not servable" from "below the floor". The file's parent directory is created if needed, and it is strict JSON (a non-numeric value is written as `null`). The mean acceptance length is checked against the floor and written at full precision; only the log rounds it. ### Usage ```yaml task_2: script: common/specdec/vllm_smoke_test.sh environment: - HF_MODEL_CKPT: <<global_vars.hf_model>> - DRAFT_CKPT_DIR: <<global_vars.output_dir>> # newest export, final preferred - SPEC_METHOD: "dflash" - NUM_SPEC_TOKENS: "7" - MIN_ACCEPTANCE_LENGTH: "1.5" - SMOKE_JSON: <<global_vars.output_dir>>/smoke_check.json - SERVER_TIMEOUT: "900" # optional; default 180 s ``` ### Testing - `tools/launcher/tests/test_service_utils.py`: `latest_checkpoint` with a dash in a parent directory, `final` winning over steps, numeric rather than string order, and no checkpoint at all (3 cases). - `tools/launcher/tests/test_vllm_smoke_test.py` runs the script as rank 0 from a directory with no `modules/` (stubbed `pip` and `nvidia-smi`), up to the paths that stop before vLLM starts (6 cases). Against the script without these fixes, all 6 fail: - It reaches `draft_missing` rather than stopping at `source`. - `MIN_ACCEPTANCE_LENGTH` of `1,5` or `nan`, `NUM_SPEC_TOKENS` of `x` or `08` and `SERVER_TIMEOUT=15m` each fail as `invalid_config` with a strict-JSON `SMOKE_JSON`. Before, `NUM_SPEC_TOKENS=x` crashed in the `EXIT` trap and wrote no JSON. - `bash -n` on all four scripts. Launcher unit suite on this commit: 192 passed. - **GPU (OCI-JHB, GB300, vLLM v0.31.0)**, through `hf_online_dflash2.yaml`'s smoke task ([4/8]) and one smoke-only submission, six runs in all: - `latest_checkpoint` picked `exported-checkpoint-final` in every training run. - Per-prompt tok/s printed (e.g. 335 tok/s average), 8/8 prompts passed. - Mean acceptance length 1.68–1.79 against the 1.5 floor; `smoke_check.json` written each time. - **GPU, Qwen3.8-27B + DFlash2 (same cluster and image):** four smoke runs at the old fixed 180 s each wrote `smoke_check.json` with `stage: server_timeout`. A fifth with `SERVER_TIMEOUT=900` passed at AL 1.76. - Not run on GPU: - the `server_died` and no-drafts failure paths. They exit through the same `write_smoke_json` trap as the passing path; - creating `SMOKE_JSON`'s parent directory. A smoke-only run hit the missing directory before this was added; the rerun used an existing directory. ### Before your PR is "*Ready for review*" Make sure you read and follow [Contributor guidelines](https://github.com/NVIDIA/Model-Optimizer/blob/main/CONTRIBUTING.md) and your commits are signed (`git commit -s -S`). Make sure you read and follow the [Security Best Practices](https://github.com/NVIDIA/Model-Optimizer/blob/main/SECURITY.md#security-coding-practices-for-contributors) (e.g. avoiding hardcoded `trust_remote_code=True`, `torch.load(..., weights_only=False)`, `pickle`, etc.). - Is this change backward compatible?: ✅ (`SMOKE_JSON` is optional. With `MIN_ACCEPTANCE_LENGTH` set, a run with no speculative drafts now fails instead of passing; that was the bug.) - If you copied code from any other sources or added a new PIP dependency, did you follow guidance in `CONTRIBUTING.md`: N/A - Did you write any new necessary tests?: ✅ (`latest_checkpoint`; the smoke script itself is validated on GPU as above) - Did you update [Changelog](https://github.com/NVIDIA/Model-Optimizer/blob/main/CHANGELOG.rst)?: N/A - Did you get Claude approval on this PR?: ❌ - not yet run ### Additional Information - The `specdec-release` skill's `gate_smoke.py` ([6/8]) reads `SMOKE_JSON`.   ## Summary by CodeRabbit * **Improvements** * Checkpoint selection now prefers a `final` checkpoint, or otherwise chooses the highest-numbered checkpoint. * Smoke tests validate numeric settings, use a configurable server timeout, and report run results, failure reasons, and performance metrics in an optional JSON file. * Acceptance-length checks now use cumulative draft and accepted-token counts; prompt failures and unmet acceptance thresholds result in a failed test. * **Tests** * Added coverage for checkpoint selection and smoke-test configuration failures.  --------- Signed-off-by: Zhehao Hu <zhehaoh@nvidia.com> Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>

Zhehao-Hu force-pushed the zhehaoh/specdec-gates-train branch from 296cd73 to 7c74a44 Compare October 22, 2026 18:00

Zhehao-Hu force-pushed the zhehaoh/specdec-gates-bench branch 2 times, most recently from 160f9ed to 3fe37d2 Compare October 22, 2026 22:09

Zhehao-Hu force-pushed the zhehaoh/specdec-gates-train branch from 7c74a44 to 279c27c Compare October 22, 2026 22:09

Zhehao-Hu force-pushed the zhehaoh/specdec-gates-bench branch from 3fe37d2 to c87329b Compare October 23, 2026 00:09

Zhehao-Hu force-pushed the zhehaoh/specdec-gates-train branch from 403f2eb to b056d6b Compare October 23, 2026 04:51

Zhehao-Hu force-pushed the zhehaoh/specdec-gates-bench branch from c87329b to 1990db8 Compare October 23, 2026 04:51

Zhehao-Hu force-pushed the zhehaoh/specdec-gates-train branch from b056d6b to 28f42f0 Compare October 23, 2026 21:24

Zhehao-Hu force-pushed the zhehaoh/specdec-gates-bench branch from 1990db8 to 1146ba9 Compare October 23, 2026 21:24

Zhehao-Hu and others added 2 commits October 23, 2026 21:33

Zhehao-Hu force-pushed the zhehaoh/specdec-gates-train branch from 28f42f0 to bc2119d Compare October 23, 2026 21:35

Zhehao-Hu force-pushed the zhehaoh/specdec-gates-bench branch from 1146ba9 to 6d934c1 Compare October 23, 2026 21:35

Navigation Menu

Repository navigation

[7/8] specdec-release: add A|B benchmark validity gate and greedy-match report - #2935

[7/8] specdec-release: add A|B benchmark validity gate and greedy-match report#2935
Zhehao-Hu wants to merge 2 commits into
zhehaoh/specdec-gates-trainfrom
zhehaoh/specdec-gates-bench

Zhehao-Hu commented Oct 22, 2026 •

edited

Loading

Uh oh!

copy-pr-bot Bot commented Oct 22, 2026

Uh oh!

coderabbitai Bot commented Oct 22, 2026

Draft PR not reviewed

Uh oh!

This branch has not been deployed

Reviewers

Uh oh!

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Conversation

Zhehao-Hu commented Oct 22, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

What does this PR do?

Usage

Testing

Before your PR is "Ready for review"

Additional Information

Uh oh!

copy-pr-bot Bot commented Oct 22, 2026

Uh oh!

coderabbitai Bot commented Oct 22, 2026

Draft PR not reviewed

Uh oh!

This branch has not been deployed

Reviewers

Uh oh!

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Zhehao-Hu commented Oct 22, 2026 •

edited

Loading