History

Yuwen Hu 68a770745b Add moonlight GPU example (#12929 ) * Add moonlight GPU example and update table * Small fix * Fix based on comments * Small fix		2025-03-05 11:31:14 +08:00
..
aquila	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
aquila2	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
baichuan	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
baichuan2	Add `--modelscope` in GPU examples for minicpm, minicpm3, baichuan2 (#12564 )	2024-12-19 17:25:46 +08:00
bluelm	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
chatglm2	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
chatglm3	Polish Readme for ModelScope-related examples (#12603 )	2024-12-26 10:52:47 +08:00
chinese-llama2	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
codegeex2	Polish Readme for ModelScope-related examples (#12603 )	2024-12-26 10:52:47 +08:00
codegemma	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
codellama	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
codeshell	fix: add run oneAPI instruction for the example of codeshell (#11828 )	2024-08-16 14:29:06 +08:00
cohere	Fix cohere model on transformers>=4.41 (#11575 )	2024-07-17 17:18:59 -07:00
deciLM-7b	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
deepseek	Update Deepseek coder GPU example (#12712 )	2025-01-16 14:05:31 +08:00
dolly-v1	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
dolly-v2	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
falcon	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
flan-t5	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
gemma	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
gemma2	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
glm-edge	Add --modelscope option for glm-v4 MiniCPM-V-2_6 glm-edge and internvl2 (#12583 )	2024-12-20 13:54:17 +08:00
glm4	Polish Readme for ModelScope-related examples (#12603 )	2024-12-26 10:52:47 +08:00
gpt-j	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
internlm	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
internlm2	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
llama2	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
llama3	Update llama example information (#12640 )	2025-01-02 13:48:39 +08:00
llama3.1	Update llama example information (#12640 )	2025-01-02 13:48:39 +08:00
llama3.2	Update llama example information (#12640 )	2025-01-02 13:48:39 +08:00
minicpm	Polish Readme for ModelScope-related examples (#12603 )	2024-12-26 10:52:47 +08:00
minicpm3	Polish Readme for ModelScope-related examples (#12603 )	2024-12-26 10:52:47 +08:00
mistral	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
mixtral	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
moonlight	Add moonlight GPU example (#12929 )	2025-03-05 11:31:14 +08:00
mpt	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
phi-1_5	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
phi-2	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
phi-3	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
phixtral	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
qwen	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
qwen1.5	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
qwen2	Add `--modelscope` in GPU examples for glm4, codegeex2, qwen2 and qwen2.5 (#12561 )	2024-12-19 10:00:39 +08:00
qwen2.5	Add `--modelscope` in GPU examples for glm4, codegeex2, qwen2 and qwen2.5 (#12561 )	2024-12-19 10:00:39 +08:00
redpajama	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
replit	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
rwkv4	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
rwkv5	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
solar	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
stablelm	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
starcoder	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
vicuna	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
yi	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
yuan2	Remove env variable `BIGDL_LLM_XMX_DISABLED` in documentation (#12445 )	2024-11-27 11:16:36 +08:00
README.md	Update GPU HF-Transformers example structure (#11526 )	2024-07-08 17:58:06 +08:00

README.md

IPEX-LLM Transformers INT4 Optimization for Large Language Model on Intel GPUs

You can use IPEX-LLM to run almost every Huggingface Transformer models with INT4 optimizations on your laptops with Intel GPUs. This directory contains example scripts to help you quickly get started using IPEX-LLM to run some popular open-source models in the community. Each model has its own dedicated folder, where you can find detailed instructions on how to install and run it.