AAdrien ToupetFix #437: Catch ValueError in bitsandbytes compatibility shim
| 文件 | 最后提交记录 | 最后更新时间 |
|---|---|---|
Simplify __init__.py files + fix dependencies + add pyproject.toml - Clean up all __init__.py files to remove commented code and unnecessary imports - Root __init__.py now only exports NODE_CLASS_MAPPINGS and NODE_DISPLAY_NAME_MAPPINGS - Remove unused dependencies: pytorch-extension (replaced by custom implementations) and peft - Fix diffusers version syntax (remove 'v' prefix) - Add pyproject.toml for ComfyUI registry compliance | 1 年前 | |
Fix MPS/macOS compatibility for GGUF models (#401) - CompatibleDiT now converts ALL model params to compute_dtype on MPS (previously only FP8 - GGUF models had mixed FP16/BF16 causing hangs) - Replace MPS autocast with explicit dtype conversion in VAE encode/decode - Skip DiT autocast on MPS (CompatibleDiT handles dtype internally) - Guard call_rope_with_stability CUDA autocast for non-CUDA devices - Add weights_only=True to torch.load (FutureWarning fix) - Rename FP8CompatibleDiT → CompatibleDiT Addresses M4 Pro macOS hang at EulerSampler 0% with GGUF models | 9 个月前 | |
Fix #437: Catch ValueError in bitsandbytes compatibility shim Add ValueError to exception handling to catch packaging.InvalidVersion errors during Intel Gaudi version detection on non-Gaudi systems. | 9 个月前 | |
feat: Add deterministic generation with seed control and CFG scale parameter Core Changes: - Implement deterministic generation with phase-specific seeding strategy * VAE encoding: seed+1M for deterministic sampling without quality loss * DiT upscaling: base seed for reproducible noise generation - Add cfg_scale parameter for user control of upscaling strength (WIP) - Fix ComfyUI V3 unique_id extraction using get_executing_context().node_id Improvements: - Standardize Optional['Debug'] type hints across codebase - Make debug parameter required where it's essential (generate, infer) - Remove legacy get_unique_id() stack inspection approach - Add seed and cfg_scale logging for transparency - Fix FP8CompatibleDiT parameter order consistency - Refine input/latent noise scale steps (0.01 → 0.001 for finer control) | 11 个月前 | |
feat: Add deterministic generation with seed control and CFG scale parameter Core Changes: - Implement deterministic generation with phase-specific seeding strategy * VAE encoding: seed+1M for deterministic sampling without quality loss * DiT upscaling: base seed for reproducible noise generation - Add cfg_scale parameter for user control of upscaling strength (WIP) - Fix ComfyUI V3 unique_id extraction using get_executing_context().node_id Improvements: - Standardize Optional['Debug'] type hints across codebase - Make debug parameter required where it's essential (generate, infer) - Remove legacy get_unique_id() stack inspection approach - Add seed and cfg_scale logging for transparency - Fix FP8CompatibleDiT parameter order consistency - Refine input/latent noise scale steps (0.01 → 0.001 for finer control) | 11 个月前 | |
perf(mps): eliminate sync overhead from CPU tensor offload on unified memory - Skip CPU tensor offload on MPS (no memory benefit, causes sync stall) - Keep input_images and final_video on MPS device - Add explicit MPS sync at phase boundaries for accurate timing - Preload text embeddings before Phase 1 to avoid Phase 2 stall - Skip model→CPU movement before deletion on MPS cleanup | 9 个月前 | |
perf: in-place tensor ops to reduce memory allocation overhead - Use in-place clamp/mul/add in postprocess normalization - Use in-place clamp and Normalize in video transform pipeline - Consolidate optimized channel permute functions in performance.py - Use native permute() instead of einops rearrange in VAE encode/decode - In-place wavelet decomposition and reconstruction operations - Remove unused temporal_latent_blending function | 10 个月前 |