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
Jason Dai
7e29edcc4b
Update Readme ( #12730 )
2025-01-22 08:43:32 +08:00
Yishuo Wang
6789e5d92f
small fix ( #12727 )
2025-01-21 17:27:18 +08:00
Jason Dai
412bfd6644
Update readme ( #12724 )
2025-01-21 10:59:14 +08:00
Wang, Jian4
716d4fe563
Add vllm 0.6.2 vision offline example ( #12721 )
...
* add vision offline example
* add to docker
2025-01-21 09:58:01 +08:00
Yishuo Wang
085974e307
fix nf4 to cpu ( #12722 )
2025-01-21 09:23:22 +08:00
Yuwen Hu
9aa4be8ced
Update runtime configuration on MTL ( #12720 )
2025-01-20 11:06:37 +08:00
Yishuo Wang
bda87c21eb
add support and optimization for minicpmo audio part ( #12716 )
2025-01-16 16:39:00 +08:00
Shaojun Liu
53aae24616
Add note about enabling Resizable BAR in BIOS for GPU setup ( #12715 )
2025-01-16 16:22:35 +08:00
Yuwen Hu
534e0e6774
Update dependency for PyTorch 2.6 RC support for woq int4 ( #12714 )
2025-01-16 15:51:57 +08:00
Zhao Changmin
54d6328b3c
woq int4 fwd ( #12711 )
2025-01-16 15:48:05 +08:00
Yishuo Wang
b62734748f
add support and optimization for minicpmo vision part ( #12713 )
2025-01-16 14:51:00 +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
Yuwen Hu
9d65dcd7ef
Fix deepseek coder with linear rope type support on GPU ( #12709 )
...
* Fix deepseek coder with linear rope type
* Style fix
* Move to optimize_pre
* Small fix
* Small fix
* Small fix to not affect other cases
* Style fixes
* Update function name
* Small fix
* Small fix
* Small fix
* Fix for low transformers version first
* Style fix
* Small fix
2025-01-15 21:12:34 +08:00
binbin Deng
36bf3d8e29
[NPU doc] Update ARL product in QuickStart ( #12708 )
2025-01-15 15:57:06 +08:00
Cengguang Zhang
9930351112
LLM: add new qtype woq_int4 to support gemm int4 temporary. ( #12706 )
...
This PR add temporary qtype woq_int4 to avoid affecting other qtype and models.
Co-authored-by: leonardozcm <leonardo1997zcm@gmail.com>
2025-01-15 14:41:33 +08:00
Yuwen Hu
6d03d06ebb
Change runtime configurations for perf test on Windows ( #12705 )
...
* Change runtime configurations for perf test on Windows
* Small fix
2025-01-14 17:54:57 +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
a1da7908b9
Fix name device is not found bug ( #12703 )
2025-01-13 10:11:02 +08:00
SONG Ge
e2d58f733e
Update ollama v0.5.1 document ( #12699 )
...
* Update ollama document version and known issue
2025-01-10 18:04:49 +08:00
Yishuo Wang
db9db51e2c
fix lnl perf ( #12700 )
2025-01-10 18:00:58 +08:00
Yuwen Hu
4bf93c66e8
Support install from source for PyTorch 2.6 RC in UT ( #12697 )
...
* Support install from source for PyTorch 2.6 RC in UT
* Remove expecttest
2025-01-10 16:44:18 +08:00
binbin Deng
da8bcb7db1
[NPU ] fix load logic of glm-edge models ( #12698 )
2025-01-10 16:08:37 +08:00
joan726
584c1c5373
Update B580 CN doc ( #12695 )
2025-01-10 11:20:47 +08:00
Jason Dai
cbb8e2a2d5
Update documents ( #12693 )
2025-01-10 10:47:11 +08:00
Yishuo Wang
f8dc408888
fix user issue ( #12692 )
2025-01-10 10:18:47 +08:00
Yishuo Wang
68857494a5
refactor to simplify following upgrade 2 ( #12685 )
2025-01-10 09:29:03 +08:00
Shaojun Liu
2673792de6
Update Dockerfile ( #12688 )
2025-01-10 09:01:29 +08:00
Jason Dai
f9b29a4f56
Update B580 doc ( #12691 )
2025-01-10 08:59:35 +08:00
joan726
66d4385cc9
Update B580 CN Doc ( #12686 )
2025-01-09 19:10:57 +08:00
Yuwen Hu
c24741584d
Support PyTorch 2.6 RC perf test on Windows ( #12683 )
2025-01-09 18:17:23 +08:00
Yishuo Wang
7234c9b27b
update quantize kv cache condition ( #12681 )
2025-01-09 15:23:04 +08:00
Yuwen Hu
5d8081afbc
Remove dummy model from performance tests ( #12682 )
2025-01-09 14:50:17 +08:00
Yishuo Wang
1ec40cd09e
refactor to simplify following upgrade ( #12680 )
2025-01-09 13:34:30 +08:00
Jason Dai
aa9e70a347
Update B580 Doc ( #12678 )
2025-01-08 22:36:48 +08:00
Jason Dai
c6f57ad6ed
Update README.md ( #12677 )
2025-01-08 21:55:52 +08:00
Jason Dai
2321e8d60c
Update README.md ( #12676 )
2025-01-08 21:54:31 +08:00
Yishuo Wang
5c24276fc4
fix custom kernel registration ( #12674 )
2025-01-08 17:39:17 +08:00
Yishuo Wang
a22a8c21bb
small fix and remove ununsed code about ipex ( #12671 )
2025-01-08 17:39:04 +08:00
Yishuo Wang
c11f5f0fcd
also convert SdpaAttention in optimize_model ( #12673 )
2025-01-08 16:48:03 +08:00
Shaojun Liu
2c23ce2553
Create a BattleMage QuickStart ( #12663 )
...
* Create bmg_quickstart.md
* Update bmg_quickstart.md
* Clarify IPEX-LLM package installation based on use case
* Update bmg_quickstart.md
* Update bmg_quickstart.md
2025-01-08 14:58:37 +08:00
Yishuo Wang
7dd156d292
small fix and add comment ( #12670 )
2025-01-08 10:56:50 +08:00
Yishuo Wang
ccf618ff4a
Remove all ipex usage ( #12666 )
2025-01-08 10:31:18 +08:00
logicat
0534d7254f
Update docker_cpp_xpu_quickstart.md ( #12667 )
2025-01-08 09:56:56 +08:00
Yuwen Hu
5db6f9dcde
Add option with PyTorch 2.6 RC version for testing purposes ( #12668 )
...
* Add option with PyTorch 2.6 RC version for testing purposes
* Small update
2025-01-07 18:28:55 +08:00
Yishuo Wang
f9ee7898c8
fix onednn dependency bug ( #12665 )
2025-01-07 16:26:56 +08:00
Yishuo Wang
29ad5c449e
refactor codegeex to remove ipex kernel usage ( #12664 )
2025-01-07 16:17:40 +08:00
Yuwen Hu
525b0ee991
[NPU] Tiny fixes on examples ( #12661 )
2025-01-07 14:30:38 +08:00
Yuwen Hu
ebdf19fa7e
[NPU] Further fix saving of generation config ( #12657 )
...
* Further fix saving of generation config
* Fix based on comments
* Small fix
2025-01-07 13:53:54 +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
