Yina Chen fc7f8feb83 Support compress kv (#11642) ... * mistral snapkv * update * mtl update * update * update * update * add comments * style fix * fix style * support llama * llama use compress kv * support mistral 4.40 * fix style * support diff transformers versions * move snapkv util to kv * fix style * meet comments & small fix * revert all in one * fix indent --------- Co-authored-by: leonardozcm <leonardo1997zcm@gmail.com>		2024-07-26 16:02:00 +08:00
..
cli	Refactor bigdl.llm to ipex_llm (#24)	2024-03-22 15:41:21 +08:00
ggml	Init NPU quantize method and support q8_0_rtn (#11452)	2024-07-01 13:45:07 +08:00
gptq	Refactor bigdl.llm to ipex_llm (#24)	2024-03-22 15:41:21 +08:00
langchain	Remove chatglm_C Module to Eliminate LGPL Dependency (#11178)	2024-05-31 17:03:11 +08:00
llamaindex	Llamaindex: add tokenizer_id and support chat (#10590)	2024-04-07 13:51:34 +08:00
serving	Support codegeex4-9b for lightweight-serving (#11648)	2024-07-26 09:41:03 +08:00
transformers	Support compress kv (#11642)	2024-07-26 16:02:00 +08:00
utils	Control sys.modules ipex duplicate check with BIGDL_CHECK_DUPLICATE_IMPORT (#11453)	2024-06-27 17:21:45 +08:00
vllm	Enable ipex-llm optimization for lm head (#11589)	2024-07-16 16:48:44 +08:00
__init__.py	IPEX Duplicate importer V2 (#11310)	2024-06-19 16:29:19 +08:00
convert_model.py	Refactor bigdl.llm to ipex_llm (#24)	2024-03-22 15:41:21 +08:00
format.sh	Refactor bigdl.llm to ipex_llm (#24)	2024-03-22 15:41:21 +08:00
llm_patching.py	Upgrade Peft version to 0.10.0 for LLM finetune (#10886)	2024-05-07 15:09:14 +08:00
models.py	Remove chatglm_C Module to Eliminate LGPL Dependency (#11178)	2024-05-31 17:03:11 +08:00
optimize.py	Update tests for transformers 4.36 (#10858)	2024-05-24 10:26:38 +08:00