Release v0.2.19 #178
Merged
Release v0.2.19 #178
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
## cuBLAS Dynamic Loader (Issue #134) - Dynamic loading of cuBLAS library (cublas64_13.dll / libcublas.so) - Supports GEMM: sgemm, dgemm, hgemm, gemm_ex (mixed precision) - Supports GEMV: sgemv, dgemv - Row-major convenience wrappers for Python API - Python bindings: cublas_is_available, cublas_get_version, cublas_test_* ## C++ Kernel Profiler (Issue #150) - Native C++ profiler using CUDA Driver API (cuEvent*) - ScopedTimer class for RAII-based timing - KernelProfiler for aggregating multiple kernel records - Python bindings with automatic native backend detection - Chrome trace export support Test results (RTX 5090, CUDA 13.1): - cuBLAS loaded: cublas64_13.dll v13.2.0 - SGEMM/HGEMM/DGEMM: all pass - Profiler: native C++ backend active 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add memory-mapped model loading with on-demand GPU loading for large models (70B+).
## Core Implementation (Rust)
- LazyTensor: GPU caching with LRU eviction
- LazyModelLoader: Multi-file SafeTensors loader with memory budgeting
- TensorState enum: OnDisk, Loading, OnGpu, Evicted
- Layer management: get_layer_tensors, layer_size, is_layer_loaded, layer_state
## Loading Strategies (Python)
- SimpleStreaming: Load/unload each layer (minimal VRAM)
- SlidingWindow: Keep N layers, prefetch ahead (balanced)
- AutoLRU: Automatic LRU eviction (best performance)
## API
- LazyModelLoader(memory_budget, enable_eviction)
- LayerStreamingContext for managed streaming
- create_streaming_context() factory function
## Usage
```python
loader = LazyModelLoader(memory_budget=8 * 1024**3)
loader.load_file("model.safetensors")
with LayerStreamingContext(loader, SlidingWindow(4), num_layers=32) as ctx:
for i in range(32):
ctx.prepare(i)
hidden = layers[i](hidden)
```
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove unused imports (F401) - Fix f-string without placeholders (F541) - Organize imports (I001) - Remove unnecessary mode argument (UP015) - Fix redefinition of unused import (F811) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Tests that require native CUDA module are now skipped when running in CI environment without GPU support. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
) Implements complete diffusion model support for text-to-image generation: Models: - DiT (Diffusion Transformer) with AdaLN conditioning - SD3Transformer (MMDiT architecture) - FluxTransformer with guidance embedding - VAE encoder/decoder with SafeTensors loading Schedulers: - EulerDiscreteScheduler (SDXL-style) - DDIMScheduler (deterministic/stochastic) - FlowMatchingScheduler (Rectified Flow for SD3/Flux) Operations: - GroupNorm (CPU fallback) - Cross-Attention (non-causal) - Conv2D / Conv2DTranspose (im2col) - AdaLN / AdaLN-Zero - Sinusoidal timestep embedding Text Encoders: - CLIPTextEncoder (OpenCLIP-style) - T5Encoder (T5-XXL for SD3/Flux) Pipeline: - Text2ImagePipeline with unified interface - Demo mode (works without model weights) - Batch generation support Example: - examples/image_generate.py with CLI interface 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Fix variable shadowing issue where input_ids/attention_mask were first defined as lists then reassigned to numpy arrays, confusing mypy. - Add explicit type annotations for input_ids and attention_mask - Rename intermediate list variables to ids_list and mask_list 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implement CUDA kernels for diffusion model operations: - GroupNorm: F32/BF16/FP16 variants for VAE/UNet - AdaLN/AdaLN-Zero: Adaptive Layer Normalization for DiT - Cross-Attention: Non-causal attention for text-to-image - Conv2D: im2col, col2im, 1x1 and 3x3 direct convolutions Files added: - native/ops/nn/diffusion/: groupnorm, adaln, cross_attention, conv2d kernels - native/bindings/nn/diffusion.cpp: pybind11 bindings Python ops updated to use native kernels when available: - group_norm.py, adaln.py, cross_attention.py, conv2d.py 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Fix out_channels from 4 to 8 for PixArt-Sigma (noise + variance) - Add transformer subdirectory detection for HuggingFace diffusers format - Add sharded T5 encoder detection with fallback to random embeddings - Extract first 4 channels from 8-channel noise prediction Tested with PixArt-Sigma-XL-2-512-MS: - 10 steps in 24.49s (2.449s/step) - Output: output/pixart_test.png 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
…support - Add HFT5Encoder class using transformers library for proper T5 encoding - Support sharded safetensors loading via Python safetensors library - Auto-detect tokenizer in parent/tokenizer directory - CPU fallback when PyTorch doesn't support GPU (e.g., RTX 5090) - Update pipeline to prefer HFT5Encoder over simple T5Encoder Tested with PixArt-Sigma + T5-XXL: - T5 encoder on CPU (PyTorch lacks SM120 support) - Diffusion model on GPU via PyGPUkit - 20 steps in 55.9s (2.795s/step) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add _batched_matmul_loop() for when CUTLASS fails (SM120) - Use batched_matmul in T5 self-attention (80s -> 30s) - Remove HFT5Encoder (PyTorch dependency) - T5 now uses native GPU matmul operations Performance (RTX 5090, SM120): - T5-XXL encoding: 80s -> 30s (2.7x speedup) - batched_matmul [64,512,64]@[64,64,512]: 45ms 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implements FLUX.1-schnell text-to-image generation: - FluxTransformer with 19 joint + 38 single blocks - Joint attention (image-text cross-attention) - Single attention (self-attention on concatenated sequence) - Flow matching Euler scheduler - GPU-native ops for linear, transpose, matmul, softmax Optimizations: - GPU-native transpose_4d_0213 (18x faster than numpy) - GPU-native transpose_3d_012 for K^T (22x faster) - RoPE frequency caching to avoid recomputation Known limitations: - Modulation, layer_norm, gated_residual use numpy fallback - Generation time ~420s (vs ~3s diffusers) - needs broadcast kernels 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
m96-chan
changed the title
- Remove unused N variable in dit/model.py - Fix unused conditioning variable in dit/adaln.py - Remove unused imports in flux/blocks.py - Remove unused x_np in flux/model.py - Add DiT transformer components (PixArt architecture) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The files use #pragma once but had orphaned #endif statements causing compilation errors. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
GPUArray uses nbytes() method, not size_bytes(). 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Use the project's device_memset wrapper for CUDA API abstraction. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
m96-chan
changed the title
8 tasks
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
Release v0.2.19 with FLUX.1 image generation, lazy model loading, and infrastructure improvements.
New Features
FLUX.1 Image Generation
Lazy Model Loading with Streaming
StreamingStrategy.EAGER- Load all at once (default)StreamingStrategy.PROGRESSIVE- Load during first forwardStreamingStrategy.LAYER_BY_LAYER- Minimal memory usagecuBLAS Dynamic Loader
C++ Kernel Profiler
HuggingFace T5 Encoder
DiT Architecture
New GPU Operations
transpose_4d_0213,transpose_3d_012gpu_batched_matmul,gpu_softmaxgpu_apply_ropecross_attention,conv2d,group_normFiles Changed
src/pygpukit/diffusion/- Image generation modulenative/ops/nn/diffusion/- CUDA kernels for diffusionsrc/pygpukit/llm/- Streaming strategiesnative/core/- cuBLAS loader, profilerTest Plan
🤖 Generated with Claude Code