Commit graph

Select branches

Hide pull requests

main

Mono Color

• a1e7bfc638
  Update Readme (#12770) Jason Dai 2025-02-05 19:19:57 +0800
• 0237ffb302
  refactor xpu linear forward (#12768) Yishuo Wang 2025-02-05 17:40:38 +0800
• 413d6c2b66
  Update check.py removing a twice defined function (#12760) Danciu Georgian 2025-02-05 05:37:59 +0200
• 184adb2653
  Small fix to MiniCPM-o-2_6 GPU example (#12766) Yuwen Hu 2025-02-05 11:32:26 +0800
• ee809e71df
  add troubleshooting section (#12755) Shaojun Liu 2025-01-26 11:03:58 +0800
• 5fb87d7486
  remove ${HF_TOKEN} (#12742) Shaojun Liu 2025-01-26 10:31:42 +0800
• f924880694
  vLLM: Fix vLLM-CPU docker image (#12741) Xiangyu Tian 2025-01-24 10:00:29 +0800
• 69f13c78b8
  [NPU] Update layernorm node on MTL/ARL (#12738) Yuwen Hu 2025-01-23 17:25:19 +0800
• d11f257ee7
  Add GPU example for MiniCPM-o-2_6 (#12735) Yuwen Hu 2025-01-23 16:10:19 +0800
• dcca522618
  Remove sdpa available patch (#12734) Yuwen Hu 2025-01-22 17:22:28 +0800
• c9b6c94a59
  vLLM: Update vLLM-cpu to v0.6.6-post1 (#12728) Xiangyu Tian 2025-01-22 15:03:01 +0800
• 78cca0a68c
  [NPU] update llm-npu-cli example (#12729) Ruonan Wang 2025-01-22 09:59:27 +0800
• 7e29edcc4b
  Update Readme (#12730) Jason Dai 2025-01-22 08:43:32 +0800
• 6789e5d92f
  small fix (#12727) Yishuo Wang 2025-01-21 17:27:18 +0800
• 412bfd6644
  Update readme (#12724) Jason Dai 2025-01-21 10:59:14 +0800
• 716d4fe563
  Add vllm 0.6.2 vision offline example (#12721) Wang, Jian4 2025-01-21 09:58:01 +0800
• 085974e307
  fix nf4 to cpu (#12722) Yishuo Wang 2025-01-21 09:23:22 +0800
• 9aa4be8ced
  Update runtime configuration on MTL (#12720) Yuwen Hu 2025-01-20 11:06:37 +0800
• bda87c21eb
  add support and optimization for minicpmo audio part (#12716) Yishuo Wang 2025-01-16 16:39:00 +0800
• 53aae24616
  Add note about enabling Resizable BAR in BIOS for GPU setup (#12715) Shaojun Liu 2025-01-16 16:22:35 +0800
• 534e0e6774
  Update dependency for PyTorch 2.6 RC support for woq int4 (#12714) Yuwen Hu 2025-01-16 15:51:57 +0800
• 54d6328b3c
  woq int4 fwd (#12711) Zhao Changmin 2025-01-16 15:48:05 +0800
• b62734748f
  add support and optimization for minicpmo vision part (#12713) Yishuo Wang 2025-01-16 14:51:00 +0800
• c52bdff76b
  Update Deepseek coder GPU example (#12712) Yuwen Hu 2025-01-16 14:05:31 +0800
• 9d65dcd7ef
  Fix deepseek coder with linear rope type support on GPU (#12709) Yuwen Hu 2025-01-15 21:12:34 +0800
• 36bf3d8e29
  [NPU doc] Update ARL product in QuickStart (#12708) binbin Deng 2025-01-15 15:57:06 +0800
• 9930351112
  LLM: add new qtype woq_int4 to support gemm int4 temporary. (#12706) Cengguang Zhang 2025-01-15 14:41:33 +0800
• 6d03d06ebb
  Change runtime configurations for perf test on Windows (#12705) Yuwen Hu 2025-01-14 17:54:57 +0800
• 350fae285d
  Add Qwen2-VL HF GPU example with ModelScope Support (#12606) Xu, Shuo 2025-01-13 15:42:04 +0800
• a1da7908b9
  Fix name device is not found bug (#12703) Yuwen Hu 2025-01-13 10:11:02 +0800
• e2d58f733e
  Update ollama v0.5.1 document (#12699) SONG Ge 2025-01-10 18:04:49 +0800
• db9db51e2c
  fix lnl perf (#12700) Yishuo Wang 2025-01-10 18:00:58 +0800
• 4bf93c66e8
  Support install from source for PyTorch 2.6 RC in UT (#12697) Yuwen Hu 2025-01-10 16:44:18 +0800
• da8bcb7db1
  [NPU ] fix load logic of glm-edge models (#12698) binbin Deng 2025-01-10 16:08:37 +0800
• 584c1c5373
  Update B580 CN doc (#12695) joan726 2025-01-10 11:20:47 +0800
• cbb8e2a2d5
  Update documents (#12693) Jason Dai 2025-01-10 10:47:11 +0800
• f8dc408888
  fix user issue (#12692) Yishuo Wang 2025-01-10 10:18:47 +0800
• 68857494a5
  refactor to simplify following upgrade 2 (#12685) Yishuo Wang 2025-01-10 09:29:03 +0800
• 2673792de6
  Update Dockerfile (#12688) Shaojun Liu 2025-01-10 09:01:29 +0800
• f9b29a4f56
  Update B580 doc (#12691) Jason Dai 2025-01-10 08:59:35 +0800
• 66d4385cc9
  Update B580 CN Doc (#12686) joan726 2025-01-09 19:10:57 +0800
• c24741584d
  Support PyTorch 2.6 RC perf test on Windows (#12683) Yuwen Hu 2025-01-09 18:17:23 +0800
• 7234c9b27b
  update quantize kv cache condition (#12681) Yishuo Wang 2025-01-09 15:23:04 +0800
• 5d8081afbc
  Remove dummy model from performance tests (#12682) Yuwen Hu 2025-01-09 14:50:17 +0800
• 1ec40cd09e
  refactor to simplify following upgrade (#12680) Yishuo Wang 2025-01-09 13:34:30 +0800
• aa9e70a347
  Update B580 Doc (#12678) Jason Dai 2025-01-08 22:36:48 +0800
• c6f57ad6ed
  Update README.md (#12677) Jason Dai 2025-01-08 21:55:52 +0800
• 2321e8d60c
  Update README.md (#12676) Jason Dai 2025-01-08 21:54:31 +0800
• 5c24276fc4
  fix custom kernel registration (#12674) Yishuo Wang 2025-01-08 17:39:17 +0800
• a22a8c21bb
  small fix and remove ununsed code about ipex (#12671) Yishuo Wang 2025-01-08 17:39:04 +0800
• c11f5f0fcd
  also convert SdpaAttention in optimize_model (#12673) Yishuo Wang 2025-01-08 16:48:03 +0800
• 2c23ce2553
  Create a BattleMage QuickStart (#12663) Shaojun Liu 2025-01-08 14:58:37 +0800
• 7dd156d292
  small fix and add comment (#12670) Yishuo Wang 2025-01-08 10:56:50 +0800
• ccf618ff4a
  Remove all ipex usage (#12666) Yishuo Wang 2025-01-08 10:31:18 +0800
• 0534d7254f
  Update docker_cpp_xpu_quickstart.md (#12667) logicat 2025-01-08 09:56:56 +0800
• 5db6f9dcde
  Add option with PyTorch 2.6 RC version for testing purposes (#12668) Yuwen Hu 2025-01-07 18:28:55 +0800
• f9ee7898c8
  fix onednn dependency bug (#12665) Yishuo Wang 2025-01-07 16:26:56 +0800
• 29ad5c449e
  refactor codegeex to remove ipex kernel usage (#12664) Yishuo Wang 2025-01-07 16:17:40 +0800
• 525b0ee991
  [NPU] Tiny fixes on examples (#12661) Yuwen Hu 2025-01-07 14:30:38 +0800
• ebdf19fa7e
  [NPU] Further fix saving of generation config (#12657) Yuwen Hu 2025-01-07 13:53:54 +0800
• 381d448ee2
  [NPU] Example & Quickstart updates (#12650) Yuwen Hu 2025-01-07 13:52:41 +0800
• ddc0ef3993
  refactor device check and remove cohere/mixtral support (#12659) Yishuo Wang 2025-01-07 11:15:51 +0800
• ea65e4fecc
  remove falcon support and related UT (#12656) Yishuo Wang 2025-01-07 09:26:00 +0800
• fae73eee79
  [NPU] Support save npu quantized model without npu dependency (#12647) Yina Chen 2025-01-06 12:06:22 +0200
• 502461d836
  remove unnecessary ipex kernel usage (#12649) Yishuo Wang 2025-01-03 16:45:24 +0800
• 9f8b134889
  add ipex-llm custom kernel registration (#12648) Yishuo Wang 2025-01-03 16:45:04 +0800
• 0b377100c5
  Add guide for save-load usage (#12498) binbin Deng 2025-01-03 16:30:15 +0800
• 6711a48a36
  Enable internvl2-8b on vllm(#12645) Wang, Jian4 2025-01-03 14:49:36 +0800
• 8fd2dcba86
  Add benchmark_util for transformers >= 4.47.0 (#12644) Zijie Li 2025-01-03 10:48:29 +0800
• 550fa01649
  [Doc] Update ipex-llm ollama troubleshooting for v0.4.6 (#12642) SONG Ge 2025-01-02 17:28:54 +0800
• 8e5328e9b4
  add disable opts for awq (#12641) Yina Chen 2025-01-02 09:45:22 +0200
• 62318964fa
  Update llama example information (#12640) Xu, Shuo 2025-01-02 13:48:39 +0800
• 81211fd010
  remove unused code (#12635) Yishuo Wang 2025-01-02 13:31:09 +0800
• 534566e290
  [NPU] Support minicpm-v with python cpp backend (#12637) binbin Deng 2025-01-02 11:13:15 +0800
• f289f68d57
  small fix (#12634) Yishuo Wang 2024-12-30 17:14:25 +0800
• 2d08155513
  remove bmm, which is only required in ipex 2.0 (#12630) Yishuo Wang 2024-12-27 17:28:57 +0800
• f17ccfa61a
  [NPU] Fix save-load usage of minicpm models (#12628) binbin Deng 2024-12-27 15:56:46 +0800
• c72a5db757
  remove unused code again (#12624) Yishuo Wang 2024-12-27 14:17:11 +0800
• 46eeab4479
  [NPU] Fix regression caused by layer_norm change (#12627) binbin Deng 2024-12-27 14:08:49 +0800
• 90f6709486
  [remove pipeline examples (#12626) Ruonan Wang 2024-12-26 21:42:28 -0800
• 5f04ed7254
  NPU] Update prompt format for baichuan2-pipeline (#12625) Zijie Li 2024-12-27 11:30:54 +0800
• 34dbdb8ee3
  small fix (#12623) Yishuo Wang 2024-12-27 10:19:27 +0800
• 55ce091242
  Add GLM4-Edge-V GPU example (#12596) Xu, Shuo 2024-12-27 09:40:29 +0800
• 796ee571a5
  [NPU doc] Update verified platforms (#12621) binbin Deng 2024-12-26 17:39:13 +0800
• bbdbbb0d88
  [NPU] Compatible with other third-party models like auto-round (#12620) Ruonan Wang 2024-12-26 01:25:18 -0800
• a9abde0b5d
  support passing attn_scale to sdpa (#12619) Yishuo Wang 2024-12-26 16:58:09 +0800
• 40a7d2b4f0
  Consolidated C-Eval Benchmark Guide for Single-GPU and Multi-GPU Environments (#12618) Shaojun Liu 2024-12-26 15:23:32 +0800
• ccc4055058
  [NPU] Update prompt format for baichuan2 (#12615) Zijie Li 2024-12-26 11:41:37 +0800
• 1604b4ead8
  small fix (#12616) Yishuo Wang 2024-12-26 11:35:12 +0800
• d841e1dc0d
  [NPU] update convert script based on latest usage (#12617) Ruonan Wang 2024-12-25 19:23:04 -0800
• ef585d3360
  Polish Readme for ModelScope-related examples (#12603) Xu, Shuo 2024-12-26 10:52:47 +0800
• 28737c250c
  Update Dockerfile (#12585) Shaojun Liu 2024-12-26 10:20:52 +0800
• a596f1ae5f
  remove bigdl-llm test to fix langchain UT (#12613) Yishuo Wang 2024-12-26 10:17:25 +0800
• 9e895f04ec
  [NPU] fix npu save (#12614) Ruonan Wang 2024-12-25 17:21:16 -0800
• 0477fe6480
  [docs] Update doc for latest open webui: 0.4.8 (#12591) Mingqi Hu 2024-12-26 09:18:20 +0800
• 6249c1e373
  rewrite llama optimization (#12609) Yishuo Wang 2024-12-25 17:04:32 +0800
• 5f5ac8a856
  fix llama related import (#12611) Yishuo Wang 2024-12-25 16:23:52 +0800
• 54b1d7d333
  Update README.zh-CN.md (#12610) Jason Dai 2024-12-25 15:38:59 +0800
• 4e6b9d804f
  add compresskv back for mistral (#12607) Yishuo Wang 2024-12-25 11:06:08 +0800
• 9c9800be31
  Update README.zh-CN.md (#12570) joan726 2024-12-24 20:32:36 +0800