tzhouam 3c52432100 Merge branch 'main' into dev/vllm-align

2026-03-20 01:38:43 +00:00

..

__init__.py

Int8 Quantization Support for DiT (Z-Image & Qwen-Image) (#1470)

2026-03-19 22:58:29 +08:00

base.py

Update vLLM precompiled wheel version and refactor various components for improved functionality and error handling. Changes include modifying the get_name method in DiffusionQuantizationConfig to use class-level attributes, enhancing metadata handling in StageEngineCoreClient, and adjusting the AsyncOmni class constructor for better parameter management. Additionally, improved error handling in omni_snapshot_download and optimized initial chunk size computation in talker2code2wav_async_chunk for dynamic load adaptation.

2026-03-19 05:14:34 +00:00

fp8.py

[Feature]: FP8 Quantization Support for DiT (#1034)

2026-02-11 21:01:35 +08:00

gguf.py

[Feature]: Native GGUF Quantization Support for DiT (#1285)

2026-02-27 11:39:14 +08:00

int8.py

Int8 Quantization Support for DiT (Z-Image & Qwen-Image) (#1470)

2026-03-19 22:58:29 +08:00