Ke Wen 862bcff833 Support loading of larger models with on-the-fly quantization (#3061)

2025-01-22 21:33:17 -08:00

..

__init__.py

Update model_loader deps and qqq quantization deps (#2220) (#2318)

2024-12-02 23:22:13 +08:00

loader.py

Support loading of larger models with on-the-fly quantization (#3061)

2025-01-22 21:33:17 -08:00

utils.py

Update model_loader deps and qqq quantization deps (#2220) (#2318)

2024-12-02 23:22:13 +08:00

weight_utils.py

Fix the FP8 E4M3 parsing offline scales failure bug (#3045)

2025-01-22 14:19:33 -08:00