ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1
ipex-llm/python/llm/src/ipex_llm/transformers
History
Shaojun Liu 2cce89691a
Enable use_batch_forward Optimization on Battlemage GPU (#12516) 
* Update get_xpu_device_type() to support bmg

* enable use_batch_forward for bmg

* Update low_bit_linear.py

* Update utils.py

* use batch kernel for fp8e5
2024-12-12 12:44:36 +08:00
..
awq Refactor bigdl.llm to ipex_llm (#24) 2024-03-22 15:41:21 +08:00
gguf IPEX Duplicate importer V2 (#11310) 2024-06-19 16:29:19 +08:00
layers Divide core-xe packages (#11131) 2024-05-28 12:00:18 +08:00
models support new model (#12523) 2024-12-11 13:41:15 +08:00
npu_models [NPU] fix transpose_value = False for NPU optimize_model=True (#12525) 2024-12-11 15:51:39 +08:00
npu_pipeline_model [NPU] Fix minicpm-2B error (#12527) 2024-12-11 16:49:32 +08:00
__init__.py Refactor fastapi-serving and add one card serving(#11581) 2024-07-17 11:12:43 +08:00
bmm.py Divide core-xe packages (#11131) 2024-05-28 12:00:18 +08:00
convert.py support new model (#12523) 2024-12-11 13:41:15 +08:00
convert_ipex.py LLM: Fix bigdl_ipex_int8 warning (#10890) 2024-04-26 11:18:44 +08:00
embedding.py add save_low_bit support for DiskEmbedding (#11621) 2024-07-19 10:34:53 +08:00
kv.py llama 3.1/3.2 support compresskv (#12347) 2024-11-06 17:33:43 +08:00
lisa.py LISA Finetuning Example (#10743) 2024-04-18 13:48:10 +08:00
load_config.yaml Adding load_low_bit interface for ipex_llm_worker (#11000) 2024-05-13 15:30:19 +08:00
loader.py Add half precision for fastchat models (#11130) 2024-05-24 15:41:14 +08:00
lookup.py Optimize with new batch kernel when batch_size=1 on LNL (#12419) 2024-11-21 16:21:35 +08:00
low_bit_linear.py Enable use_batch_forward Optimization on Battlemage GPU (#12516) 2024-12-12 12:44:36 +08:00
model.py Patch sdpa check function in specific module attributes table (#12285) 2024-10-29 18:41:09 +08:00
modelling_bigdl.py Remove chatglm_C Module to Eliminate LGPL Dependency (#11178) 2024-05-31 17:03:11 +08:00
npu_model.py [NPU] Support glm-edge models (#12511) 2024-12-09 14:06:27 +08:00
patches.py Patch sdpa check function in specific module attributes table (#12285) 2024-10-29 18:41:09 +08:00
pipeline_parallel.py Add missing arguments in pipeline parallel generate method (#12142) 2024-11-18 13:50:18 +08:00
qlora.py Upgrade Peft version to 0.10.0 for LLM finetune (#10886) 2024-05-07 15:09:14 +08:00
relora.py Refactor bigdl.llm to ipex_llm (#24) 2024-03-22 15:41:21 +08:00
speculative.py Support performance mode of GLM4 model (#12401) 2024-11-18 18:46:52 +08:00
streamer.py [LLM]Reopen autotp generate_stream (#11120) 2024-05-24 17:16:14 +08:00
training_patch.py Fix error during merging adapter (#11145) 2024-05-27 19:41:42 +08:00
utils.py Enable use_batch_forward Optimization on Battlemage GPU (#12516) 2024-12-12 12:44:36 +08:00
xpu_customize_fwd.py Refactor bigdl.llm to ipex_llm (#24) 2024-03-22 15:41:21 +08:00