Tsukasa OI 58d5b3f514

[Model][Quantization] Restore MoE + GGUF models support (incl. Qwen3 MoE) by allowing Sideload Parameters (#30116) ...

Signed-off-by: Tsukasa OI <floss_llm@irq.a4lg.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

2025-12-09 05:30:05 +00:00

..

__init__.py

Default model load/config/tokenizer to mistral format if relevant files exist (#28659)

2025-11-21 13:58:59 -08:00

base_loader.py

…

bitsandbytes_loader.py

…

default_loader.py

[Chore]: Reorganize model repo operating functions in transformers_utils (#29680)

2025-11-28 08:46:51 -08:00

dummy_loader.py

…

gguf_loader.py

[Model][Quantization] Restore MoE + GGUF models support (incl. Qwen3 MoE) by allowing Sideload Parameters (#30116)

2025-12-09 05:30:05 +00:00

online_quantization.py

…

runai_streamer_loader.py

…

sharded_state_loader.py

[log] add weights loading time log to sharded_state loader (#28628)

2025-11-21 21:06:09 +00:00

tensorizer_loader.py

…

tensorizer.py

…

tpu.py

…

utils.py

[Model][7/N] Improve all pooling task | Deprecation as_reward_model. Extract hidden states prefer using new multi-vector retrieval API (#26686)

2025-12-08 08:10:09 +00:00

weight_utils.py

update torchao safetensors impl (#30155)

2025-12-09 12:46:35 +08:00