ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1
4060 commits 1 branch 0 tags 37 MiB
Commit graph

711 commits

Author SHA1 Message Date
Guancheng Fu
d222eaffd7
Update README.md (#13113) 2025-04-27 17:13:18 +08:00
Guancheng Fu
0cfdd399e7
Update README.md (#13104) 2025-04-24 10:21:17 +08:00
Guancheng Fu
14cd613fe1
Update vLLM docs with some new features (#13092) 
* done

* fix

* done

* Update README.md
 2025-04-22 14:39:28 +08:00
Yuwen Hu
0801d27a6f
Remove PyTorch 2.3 support for Intel GPU (#13097) 
* Remove PyTorch 2.3 installation option for GPU

* Remove xpu_lnl option in installation guides for docs

* Update BMG quickstart

* Remove PyTorch 2.3 dependencies for GPU examples

* Update the graphmode example to use stable version 2.2.0

* Fix based on comments
 2025-04-22 10:26:16 +08:00
Ruonan Wang
27d669210f
remove fschat in EAGLE example (#13005) 
* update fschat version

* fix
 2025-03-25 15:48:48 +08:00
Heyang Sun
cd109bb061
Gemma QLoRA example (#12969) 
* Gemma QLoRA example

* Update README.md

* Update README.md

---------

Co-authored-by: sgwhat <ge.song@intel.com>
 2025-03-14 14:27:51 +08:00
Yuwen Hu
7c0c77cce3
Tiny fixes (#12936) 2025-03-05 14:55:26 +08:00
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
Yuwen Hu
443cb5d4e0
Update Janus-Pro GPU example (#12906) 2025-02-28 15:39:03 +08:00
Xin Qiu
e946127613
glm 4v 1st sdp for vision (#12904) 
* glm4v 1st sdp

* update glm4v example

* meet code review

* fix style
 2025-02-28 13:23:27 +08:00
Guancheng Fu
02ec313eab
Update README.md (#12877) 2025-02-24 09:59:17 +08:00
Xu, Shuo
1e00bed001
Add GPU example for Janus-Pro (#12869) 
* Add example for Janus-Pro

* Update model link

* Fixes

* Fixes

---------

Co-authored-by: ATMxsp01 <shou.xu@intel.com>
Co-authored-by: Yuwen Hu <yuwen.hu@intel.com>
 2025-02-21 18:36:50 +08:00
binbin Deng
8077850452
[NPU GGUF] Add simple example (#12853) 2025-02-21 09:58:00 +08:00
Guancheng Fu
4eed0c7d99
initial implementation for low_bit_loader vLLM (#12838) 
* initial

* add logic for handling tensor parallel models

* fix

* Add some comments

* add doc

* fix done
 2025-02-19 19:45:34 +08:00
Xiangyu Tian
b26409d53f
R1 Hybrid: Add Benchmark for DeepSeek R1 transformers example (#12854) 
* init

* fix

* update

* update

* fix

* fix
 2025-02-19 18:33:21 +08:00
Xiangyu Tian
93c10be762
LLM: Support hybrid convert for DeepSeek V3/R1 (#12834) 
LLM: Support hybrid convert for DeepSeek V3/R1
 2025-02-19 11:31:19 +08:00
Xiangyu Tian
09150b6058
Initiate CPU-XPU Hybrid Inference for DeepSeek-R1 (#12832) 
Initiate CPU-XPU Hybrid Inference for DeepSeek-R1 with DeepseekV3Attention
and DeepseekV3MLP to XPU
 2025-02-18 13:34:14 +08:00
Xiangyu Tian
09ed96082b
Add DeepSeek V3/R1 CPU example (#12836) 
Add DeepSeek V3/R1 CPU example for bf16 model
 2025-02-18 12:45:49 +08:00
Yina Chen
eb2df5ed70
common.h -> npu/npu_common.h (#12800) 2025-02-10 14:38:22 +08:00
binbin Deng
3fee838b14
[NPU] Fix of c++ convert example (#12797) 2025-02-10 11:17:58 +08:00
Kai Huang
468d3f22fc
Rename NPU public example to llm-cli (#12790) 
* rename to llm-cli

* update readme
 2025-02-08 10:19:59 +08:00
Ruonan Wang
e90a9ad196
[NPU] Support non-const parameter for decoder layers when keep_ir=True (#12789) 
* support layernorm=False for decoder layers

* renbame to meet review

* fix style

* rename to const_parameter

* fix rebase error

* fix rebase error
 2025-02-08 09:58:42 +08:00
Yishuo Wang
8aea5319bb
update more lora example (#12785) 2025-02-08 09:46:48 +08:00
binbin Deng
6ff7faa781
[NPU] Update deepseek support in python examples and quickstart (#12786) 2025-02-07 11:25:16 +08:00
Ruonan Wang
b4f2be2b09
[NPU] Update C++ example to add DeepSeek-R1 (#12787) 2025-02-07 11:23:34 +08:00
Yishuo Wang
d0d9c9d636
remove load_in_8bit usage as it is not supported a long time ago (#12779) 2025-02-07 11:21:29 +08:00
Yishuo Wang
b4c9e23f73
fix galore and peft finetune example (#12776) 2025-02-06 16:36:13 +08:00
Yishuo Wang
c0d6b282b8
fix lisa finetune example (#12775) 2025-02-06 16:35:43 +08:00
Yishuo Wang
2e5f2e5dda
fix dpo finetune (#12774) 2025-02-06 16:35:21 +08:00
Yishuo Wang
9697197f3e
fix qlora finetune example (#12769) 2025-02-06 11:18:28 +08:00
Ruonan Wang
094a25b740
[NPU] Expose parameter to control blob / IR save logic (#12767) 
* update api

* fix convert.py

* fix style

* remove unnecessary bin file

* fix style
 2025-02-06 10:07:45 +08:00
Yuwen Hu
184adb2653
Small fix to MiniCPM-o-2_6 GPU example (#12766) 2025-02-05 11:32:26 +08:00
Yuwen Hu
d11f257ee7
Add GPU example for MiniCPM-o-2_6 (#12735) 
* Add init example for omni mode

* Small fix

* Small fix

* Add chat example

* Remove lagecy link

* Further update link

* Add readme

* Small fix

* Update main readme link

* Update based on comments

* Small fix

* Small fix

* Small fix
 2025-01-23 16:10:19 +08:00
Ruonan Wang
78cca0a68c
[NPU] update llm-npu-cli example (#12729) 
* update cli example

* add license

* rename

* update readme sample output
 2025-01-22 09:59:27 +08:00
Yuwen Hu
c52bdff76b
Update Deepseek coder GPU example (#12712) 
* Update Deepseek coder GPU example

* Fix based on comment
 2025-01-16 14:05:31 +08:00
Xu, Shuo
350fae285d
Add Qwen2-VL HF GPU example with ModelScope Support (#12606) 
* Add qwen2-vl example

* complete generate.py & readme

* improve lint style

* update 1-6

* update main readme

* Format and other small fixes

---------

Co-authored-by: Yuwen Hu <yuwen.hu@intel.com>
 2025-01-13 15:42:04 +08:00
Yuwen Hu
525b0ee991
[NPU] Tiny fixes on examples (#12661) 2025-01-07 14:30:38 +08:00
Yuwen Hu
381d448ee2
[NPU] Example & Quickstart updates (#12650) 
* Remove model with optimize_model=False in NPU verified models tables, and remove related example

* Remove experimental in run optimized model section title

* Unify model table order & example cmd

* Move embedding example to separate folder & update quickstart example link

* Add Quickstart reference in main NPU readme

* Small fix

* Small fix

* Move save/load examples under NPU/HF-Transformers-AutoModels

* Add low-bit and polish arguments for LLM Python examples

* Small fix

* Add low-bit and polish arguments for Multi-Model  examples

* Polish argument for Embedding models

* Polish argument for LLM CPP examples

* Add low-bit and polish argument for Save-Load examples

* Add accuracy tuning tips for examples

* Update NPU qucikstart accuracy tuning with low-bit optimizations

* Add save/load section to qucikstart

* Update CPP example sample output to EN

* Add installation regarding cmake for CPP examples

* Small fix

* Small fix

* Small fix

* Small fix

* Small fix

* Small fix

* Unify max prompt length to 512

* Change recommended low-bit for Qwen2.5-3B-Instruct to asym_int4

* Update based on comments

* Small fix
 2025-01-07 13:52:41 +08:00
binbin Deng
0b377100c5
Add guide for save-load usage (#12498) 2025-01-03 16:30:15 +08:00
Xu, Shuo
62318964fa
Update llama example information (#12640) 
Co-authored-by: ATMxsp01 <shou.xu@intel.com>
 2025-01-02 13:48:39 +08:00
Yishuo Wang
c72a5db757
remove unused code again (#12624) 2024-12-27 14:17:11 +08:00
Ruonan Wang
90f6709486
[remove pipeline examples (#12626) 2024-12-27 13:42:28 +08:00
Zijie Li
5f04ed7254
NPU] Update prompt format for baichuan2-pipeline (#12625) 2024-12-27 11:30:54 +08:00
Xu, Shuo
55ce091242
Add GLM4-Edge-V GPU example (#12596) 
* Add GLM4-Edge-V examples

* polish readme

* revert wrong changes

* polish readme

* polish readme

* little polish in reference info and indent

* Small fix and sample output updates

* Update main readme

---------

Co-authored-by: Yuwen Hu <yuwen.hu@intel.com>
 2024-12-27 09:40:29 +08:00
binbin Deng
796ee571a5
[NPU doc] Update verified platforms (#12621) 2024-12-26 17:39:13 +08:00
Zijie Li
ccc4055058
[NPU] Update prompt format for baichuan2 (#12615) 
* Update baichuan2.py

* style fix
 2024-12-26 11:41:37 +08:00
Ruonan Wang
d841e1dc0d
[NPU] update convert script based on latest usage (#12617) 2024-12-26 11:23:04 +08:00
Xu, Shuo
ef585d3360
Polish Readme for ModelScope-related examples (#12603) 2024-12-26 10:52:47 +08:00
Xu, Shuo
b0338c5529
Add --modelscope option for glm-v4 MiniCPM-V-2_6 glm-edge and internvl2 (#12583) 
* Add --modelscope option for glm-v4 and MiniCPM-V-2_6

* glm-edge

* minicpm-v-2_6:don't use model_hub=modelscope when use lowbit; internvl2

---------

Co-authored-by: ATMxsp01 <shou.xu@intel.com>
 2024-12-20 13:54:17 +08:00
Xu, Shuo
47da3c999f
Add --modelscope in GPU examples for minicpm, minicpm3, baichuan2 (#12564) 
* Add --modelscope for more models

* minicpm

---------

Co-authored-by: ATMxsp01 <shou.xu@intel.com>
 2024-12-19 17:25:46 +08:00