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
Yuwen Hu
637543e135
Update Ollama portable zip QuickStart with troubleshooting ( #12846 )
...
* Update ollama portable zip quickstart with runtime configurations
* Small fix
* Update based on comments
* Small fix
* Small fix
2025-02-19 11:04:03 +08:00
binbin Deng
bde8acc303
[NPU] Update doc of gguf support ( #12837 )
2025-02-19 10:46:35 +08:00
Wang, Jian4
e1809a6295
Update multimodal on vllm 0.6.6 ( #12816 )
...
* add glm4v and minicpmv example
* fix
2025-02-19 10:04:42 +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
Yishuo Wang
8418450300
optimize minicpm-o's tts part ( #12833 )
2025-02-17 14:53:37 +08:00
Shaojun Liu
f7b5a093a7
Merge CPU & XPU Dockerfiles with Serving Images and Refactor ( #12815 )
...
* Update Dockerfile
* Update Dockerfile
* Ensure scripts are executable
* Update Dockerfile
* Update Dockerfile
* Update Dockerfile
* Update Dockerfile
* Update Dockerfile
* Update Dockerfile
* update
* Update Dockerfile
* remove inference-cpu and inference-xpu
* update README
2025-02-17 14:23:22 +08:00
Jason Dai
eaec64baca
Update README.md ( #12826 )
2025-02-14 21:20:57 +08:00
joan726
59e8e1e91e
Added ollama_portablze_zip_quickstart.zh-CN.md ( #12822 )
2025-02-14 18:54:12 +08:00
Jason Dai
a09552e59a
Update ollama quickstart ( #12823 )
2025-02-14 09:55:48 +08:00
Yuwen Hu
f67986021c
Update download link for Ollama portable zip QuickStart ( #12821 )
...
* Update download link for Ollama portable zip quickstart
* Update based on comments
2025-02-13 17:48:02 +08:00
Jason Dai
16e63cbc18
Update readme ( #12820 )
2025-02-13 14:26:04 +08:00
Yuwen Hu
68414afcb9
Add initial QuickStart for Ollama portable zip ( #12817 )
...
* Add initial quickstart for Ollama portable zip
* Small fix
* Fixed based on comments
* Small fix
* Add demo image for run ollama
* Update download link
2025-02-13 13:18:14 +08:00
Wang, Jian4
1083fe5508
Reenable pp and lightweight-serving serving on 0.6.6 ( #12814 )
...
* reenable pp ang lightweight serving on 066
* update readme
* updat
* update tag
2025-02-13 10:16:00 +08:00
Guancheng Fu
af693425f1
Upgrade to vLLM 0.6.6 ( #12796 )
...
* init
* update engine init
* fix serving load_in_low_bit problem
* temp
* temp
* temp
* temp
* temp
* fix
* fixed
* done
* fix
* fix all arguments
* fix
* fix throughput script
* fix
* fix
* use official ipex-llm
* Fix readme
* fix
---------
Co-authored-by: hzjane <a1015616934@qq.com>
2025-02-12 16:47:51 +08:00
Yishuo Wang
f8ab833f74
support and optimize janus pro ( #12813 )
2025-02-12 15:07:24 +08:00
Shaojun Liu
bd815a4d96
Update the base image of inference-cpp image to oneapi 2025.0.2 ( #12802 )
...
* Update Dockerfile
* Update Dockerfile
* Update Dockerfile
* Update Dockerfile
* Update Dockerfile
* Update Dockerfile
* Update Dockerfile
* Update Dockerfile
* Update Dockerfile
* Update Dockerfile
2025-02-12 14:15:08 +08:00
Yishuo Wang
73cfe293fa
add basic support for Baichuan-M1-14B-Instruct ( #12808 )
2025-02-11 17:27:42 +08:00
binbin Deng
d093b75aa0
[NPU] Update driver installation in QuickStart ( #12807 )
2025-02-11 15:49:21 +08:00
Xiangyu Tian
b70ad902b4
Fix ipex-llm CPU linear dtype not match ( #12805 )
2025-02-11 10:34:44 +08:00
Shaojun Liu
2701a9d1e3
Remove Migrated Workflows to Avoid Duplication and Confusion ( #12801 )
...
* Delete .github/actions/llm directory
* Delete .github/workflows/release-ipex-llm.yaml
* Delete .github/workflows/llm-nightly-test.yml
* Delete .github/workflows/llm_unit_tests.yml
* Delete .github/workflows/llm-binary-build.yml
* Delete .github/workflows/llm_example_tests.yml
* Delete .github/workflows/llm_performance_tests.yml
* Delete .github/workflows/manually_build.yml
* Delete .github/workflows/manually_build_for_testing.yml
* Delete .github/workflows/release-pypi.yml
2025-02-10 14:58:08 +08:00
Yina Chen
eb2df5ed70
common.h -> npu/npu_common.h ( #12800 )
2025-02-10 14:38:22 +08:00
Yishuo Wang
e4ceb722b6
fix qwen2 vl ( #12798 )
2025-02-10 13:25:53 +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
Yuwen Hu
fd28cf1672
Upgrade ipex-llm[cpp] to oneAPI 2025.0 on Windows ( #12778 )
...
* Upgrade ipex-llm[cpp] to oneAPI 2025.0
* Fit oneapi pypi dependency on Windows for now
2025-02-07 18:29:34 +08:00
binbin Deng
ca1d7b7c2c
[NPU] Support qwen models with cos_sin_input=True ( #12788 )
2025-02-07 16:41:13 +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
Xiangyu Tian
9e9b6c9f2b
Fix cpu serving docker image ( #12783 )
2025-02-07 11:12:42 +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
Jason Dai
9c0daf6396
Fix readme links ( #12771 )
2025-02-05 19:24:25 +08:00
Jason Dai
a1e7bfc638
Update Readme ( #12770 )
2025-02-05 19:19:57 +08:00
Yishuo Wang
0237ffb302
refactor xpu linear forward ( #12768 )
2025-02-05 17:40:38 +08:00
Danciu Georgian
413d6c2b66
Update check.py removing a twice defined function ( #12760 )
...
Remove duplicate function
2025-02-05 11:37:59 +08:00
Yuwen Hu
184adb2653
Small fix to MiniCPM-o-2_6 GPU example ( #12766 )
2025-02-05 11:32:26 +08:00
Shaojun Liu
ee809e71df
add troubleshooting section ( #12755 )
2025-01-26 11:03:58 +08:00
Shaojun Liu
5fb87d7486
remove ${HF_TOKEN} ( #12742 )
2025-01-26 10:31:42 +08:00
Xiangyu Tian
f924880694
vLLM: Fix vLLM-CPU docker image ( #12741 )
2025-01-24 10:00:29 +08:00
Yuwen Hu
69f13c78b8
[NPU] Update layernorm node on MTL/ARL ( #12738 )
...
* Update layernorm node on MTL/ARL
* Fix on style
2025-01-23 17:25:19 +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
Yuwen Hu
dcca522618
Remove sdpa available patch ( #12734 )
2025-01-22 17:22:28 +08:00
