Commit graph

Select branches

Hide pull requests

main

Mono Color

• 1bd431976d
  Update ollama quickstart (#10756) Ruonan Wang 2024-04-15 16:37:55 +0800
• 47622c6a92
  Fix missing export typo in linux quickstart (#10750) Kai Huang 2024-04-15 14:16:40 +0800
• 486df2764a
  Update gpu configuration (#10760) Yuwen Hu 2024-04-15 13:27:15 +0800
• b5209d3ec1
  Update example/GPU/PyTorch-Models/Model/llava/README.md (#10757) yb-peng 2024-04-15 13:01:37 +0800
• 3d561b60ac
  LLM: add enable_xetla parameter for optimize_model API (#10753) binbin Deng 2024-04-15 12:18:25 +0800
• 3590e1be83
  revert python to 3.9 for finetune image (#10758) Shaojun Liu 2024-04-15 10:37:10 +0800
• a9a6b6b7af
  Fix baichuan-13b issue on portable zip under transformers 4.36 (#10746) Jiao Wang 2024-04-12 16:27:01 -0700
• 9e668a5bf0
  fix_internlm-chat-7b-8k repo name in examples (#10747) Jiao Wang 2024-04-12 10:15:48 -0700
• c3fc8f4b90
  LLM: add bs limitation for llama softmax upcast to fp32 (#10752) binbin Deng 2024-04-12 15:40:25 +0800
• 0d518aab8d
  Merge pull request #10697 from MargarettMao/ceval hxsz1997 2024-04-12 14:37:47 +0800
• dd0d2df5af Change fp16.csv mistral-7b-v0.1 into Mistral-7B-v0.1 jenniew 2024-04-12 14:28:46 +0800
• 7309f1ddf9 Mofidy Typos jenniew 2024-04-12 14:23:13 +0800
• cb594e1fc5 Mofidy Typos jenniew 2024-04-12 14:22:09 +0800
• 382c18e600 Mofidy Typos jenniew 2024-04-12 14:15:48 +0800
• 1a360823ce Mofidy Typos jenniew 2024-04-12 14:13:21 +0800
• cdbb1de972 Mark Color Modification jenniew 2024-04-12 14:00:50 +0800
• 9bbfcaf736 Mark Color Modification jenniew 2024-04-12 13:30:16 +0800
• bb34c6e325 Mark Color Modification jenniew 2024-04-12 13:26:36 +0800
• 8086554d33
  use new fp16 sdp in llama and mistral (#10734) Yishuo Wang 2024-04-12 10:49:02 +0800
• 019293e1b9
  Fuse MOE indexes computation (#10716) Yang Wang 2024-04-11 10:12:55 -0700
• b151a9b672 edit csv_to_html to combine en & zh jenniew 2024-04-11 17:35:36 +0800
• 70ed9397f9
  LLM: fix AttributeError of FP16Linear (#10740) binbin Deng 2024-04-11 17:03:56 +0800
• 1256a2cc4e
  Add chatglm3 long input example (#10739) Keyan (Kyrie) Zhang 2024-04-11 01:33:43 -0700
• fd473ddb1b
  Merge pull request #10730 from MargarettMao/MargarettMao-parent_folder hxsz1997 2024-04-11 15:45:24 +0800
• 2d64630757
  Remove transformers version in axolotl example (#10736) Qiyuan Gong 2024-04-11 14:02:31 +0800
• 2685c41318
  Modify all-in-one benchmark (#10726) yb-peng 2024-04-11 13:38:50 +0800
• 301504aa8d
  Fix transformers version warning (#10732) Xiangyu Tian 2024-04-11 13:12:49 +0800
• 9bec233e4d
  Delete python/llm/test/benchmark/perplexity/update_html_in_parent_folder.py Wenjing Margaret Mao 2024-04-11 07:21:12 +0800
• 63a9a736be
  Merge branch 'intel-analytics:main' into MargarettMao-parent_folder Wenjing Margaret Mao 2024-04-11 07:18:19 +0800
• 50dfcaa8fa
  Update llm-ppl-evaluation.yml -- Update llm-ppl-evaluation.yml -- Update HTML file: change from ppl/update_in_parent_folder into harness/update_in_parent_folder Wenjing Margaret Mao 2024-04-11 07:15:18 +0800
• 4b024b7aac
  LLM: optimize chatglm2 8k input. (#10723) Cengguang Zhang 2024-04-10 16:59:06 +0800
• cd22cb8257
  Update Env check Script (#10709) Yuxuan Xia 2024-04-10 15:06:00 +0800
• 29bf28bd6f
  Upgrade python to 3.11 in Docker Image (#10718) Shaojun Liu 2024-04-10 14:41:27 +0800
• b727767f00
  Add axolotl v0.3.0 with ipex-llm on Intel GPU (#10717) Qiyuan Gong 2024-04-10 14:38:29 +0800
• 0ccd7bfca9
  revise quickstart (#10721) Shengsheng Huang 2024-04-10 14:24:53 +0800
• a81f9e61a6
  Revise open_webui_with_ollama_quickstart.md (#10720) yb-peng 2024-04-10 14:04:13 +0800
• c9e6d42ad1
  LLM: Fix chatglm3-6b-32k error (#10719) Wang, Jian4 2024-04-10 11:24:06 +0800
• 585c174e92
  Read the value of KV_CACHE_ALLOC_BLOCK_LENGTH from the environment variables (#10707) Keyan (Kyrie) Zhang 2024-04-09 19:48:46 -0700
• d1eaea509f
  update chatglm readme (#10659) Jiao Wang 2024-04-09 14:24:46 -0700
• 878a97077b
  Fix llava example to support transformerds 4.36 (#10614) Jiao Wang 2024-04-09 13:47:07 -0700
• 1e817926ba
  Fix low memory generation example issue in transformers 4.36 (#10702) Jiao Wang 2024-04-09 09:56:52 -0700
• 6e7da0d92c
  small fix in document Shengsheng Huang 2024-04-09 23:04:26 +0800
• 8924dbc3f9
  revise open webui quickstart and some indexes (#10715) Shengsheng Huang 2024-04-09 22:44:03 +0800
• a0244527aa
  Small updates to langchain-chatchat quickstart readme (#10714) Yuwen Hu 2024-04-09 19:37:41 +0800
• fde6ab50d0
  Further fix to python 3.11 document (#10712) Yuwen Hu 2024-04-09 19:13:01 +0800
• 447f48499a
  Init commit of open-webui quickstart (#10682) yb-peng 2024-04-09 18:21:42 +0800
• 97db2492c8
  Update setup.py for bigdl-core-xe-esimd-21 on Windows (#10705) Yuwen Hu 2024-04-09 18:21:21 +0800
• b4147a97bb
  Fix dtype mismatch error (#10609) Zhicun 2024-04-09 17:50:33 +0800
• f37a1f2a81
  Upgrade to python 3.11 (#10711) Shaojun Liu 2024-04-09 17:41:17 +0800
• 8f45e22072
  fix llama2 (#10710) Yishuo Wang 2024-04-09 17:28:37 +0800
• e10040b7f1
  upgrade to python 3.11 (#10695) Shaojun Liu 2024-04-09 17:04:42 +0800
• e438f941f2
  disable rwkv5 fp16 (#10699) Yishuo Wang 2024-04-09 16:42:11 +0800
• 6a32216269
  LLM: add llama2 8k input example. (#10696) Cengguang Zhang 2024-04-09 16:02:37 +0800
• 289cc99cd6
  Update README.md (#10700) Wenjing Margaret Mao 2024-04-09 16:01:12 +0800
• 3e4fbee87c
  Update readme & quickstart (#10685) Jason Dai 2024-04-09 15:59:17 +0800
• 39ff586454
  docs: update README.md (#10662) Ikko Eltociear Ashimine 2024-04-09 16:55:57 +0900
• d3116de0db
  Update README.md (#10701) Wenjing Margaret Mao 2024-04-09 15:50:25 +0800
• d59e0cce5c
  Migrate harness to ipexllm (#10703) Chen, Zhentao 2024-04-09 15:48:53 +0800
• 8cf26d8d08
  Update ollama_quickstart.md (#10708) yb-peng 2024-04-09 15:47:41 +0800
• 1e27e08322
  Modify example from fp32 to fp16 (#10528) Keyan (Kyrie) Zhang 2024-04-09 00:45:49 -0700
• 44922bb5c2
  LLM: support baichuan2-13b using AutoTP (#10691) binbin Deng 2024-04-09 14:06:01 +0800
• c7422712fc
  mistral 4.36 use fp16 sdp (#10704) Yina Chen 2024-04-09 13:50:33 +0800
• dcb2038aad
  Enable optimization for sentence_transformers (#10679) Ovo233 2024-04-09 12:33:46 +0800
• f03c029914
  pydantic version>=2.0.0 for llamaindex (#10694) Zhicun 2024-04-09 09:48:42 +0800
• 5a1f446d3c
  support fp8 in xetla (#10555) Yang Wang 2024-04-08 13:22:09 -0700
• 591bae092c combine english and chinese, remove nan jenniew 2024-04-08 19:37:51 +0800
• 7c43ac0164
  LLM: optimize llama natvie sdp for split qkv tensor (#10693) Cengguang Zhang 2024-04-08 17:48:11 +0800
• 1274cba79b
  stablelm fp8 kv cache (#10672) Xin Qiu 2024-04-08 15:16:46 +0800
• 65127622aa
  fix UT threshold (#10689) Yishuo Wang 2024-04-08 14:58:20 +0800
• c0cd238e40
  LLM: support llama2 8k input with w4a16. (#10677) Cengguang Zhang 2024-04-08 11:43:15 +0800
• db7c5cb78f
  update model path for spr perf test (#10687) Shaojun Liu 2024-04-08 10:21:56 +0800
• 321bc69307
  Fix llamaindex ut (#10673) Zhicun 2024-04-08 09:47:51 +0800
• a11b708135
  Modify the .md link in chatchat readthedoc (#10681) Keyan (Kyrie) Zhang 2024-04-07 01:33:32 -0700
• 2d88bb9b4b
  add test api transformer_int4_fp16_gpu (#10627) yb-peng 2024-04-07 15:47:17 +0800
• 47cabe8fcc
  LLM: Fix no return_last_logit running bigdl_ipex chatglm3 (#10678) Wang, Jian4 2024-04-07 15:27:58 +0800
• 33f90beda0
  fix quickstart docs (#10676) Shengsheng Huang 2024-04-07 14:26:59 +0800
• 9ad4b29697
  LLM: CPU benchmark using tcmalloc (#10675) Wang, Jian4 2024-04-07 14:17:01 +0800
• d9a1153b4e
  LLM: upgrade deepspeed in AutoTP on GPU (#10647) binbin Deng 2024-04-07 14:05:19 +0800
• 56dfcb2ade
  Migrate portable zip to ipex-llm (#10617) Jin Qiao 2024-04-07 13:58:58 +0800
• 9d8ba64c0d
  Llamaindex: add tokenizer_id and support chat (#10590) Zhicun 2024-04-07 13:51:34 +0800
• 10ee786920
  Replace with IPEX-LLM in example comments (#10671) Jin Qiao 2024-04-07 13:29:51 +0800
• 08018a18df
  Remove not-imported MistralConfig (#10670) Xiangyu Tian 2024-04-07 10:32:05 +0800
• 1a9b8204a4
  LLM: support int4 fp16 chatglm2-6b 8k input. (#10648) Cengguang Zhang 2024-04-07 09:39:21 +0800
• ab87b6ab21
  Update readme (#10669) Jason Dai 2024-04-07 09:13:45 +0800
• 69bdbf5806
  Fix vllm print error message issue (#10664) Jiao Wang 2024-04-05 15:08:13 -0700
• 29d97e4678
  Update readme (#10665) Jason Dai 2024-04-05 18:01:57 +0800
• ac65ab65c6
  Update llama_cpp_quickstart.md (#10663) Yang Wang 2024-04-04 11:00:50 -0700
• 6699d86192
  Update index.rst (#10660) Jason Dai 2024-04-04 20:37:33 +0800
• 8abf4da1bc
  README: Fix typo: tansformers -> transformers (#10657) Tom Aarsen 2024-04-04 02:54:48 +0200
• 4c3e493b2d
  fix stablelm2 1.6b (#10656) Xin Qiu 2024-04-03 22:15:32 +0800
• 22f09f618a
  update the video demo (#10655) Shengsheng Huang 2024-04-03 20:51:01 +0800
• 7c08d83d9e
  Update quickstart (#10654) Jason Dai 2024-04-03 20:43:22 +0800
• f84e72e7af
  revise ollama quickstart (#10653) Shengsheng Huang 2024-04-03 20:35:34 +0800
• f789c2eee4
  add ollama quickstart (#10649) yb-peng 2024-04-03 19:33:39 +0800
• 1ae519ec69
  add langchain-chatchat quickstart (#10652) Shengsheng Huang 2024-04-03 19:23:09 +0800
• 45437ddc9a
  update indexes, move some sections in coding quickstart to webui (#10651) Shengsheng Huang 2024-04-03 18:18:49 +0800
• c26e06d5cf
  update coding quickstart and webui quickstart for warmup note (#10650) Shengsheng Huang 2024-04-03 17:18:28 +0800
• 5b096c39a6
  Change style for video rendering (#10646) Yuwen Hu 2024-04-03 16:31:02 +0800
• cc8b3be11c
  Add GPU and CPU example for stablelm-zephyr-3b (#10643) Jin Qiao 2024-04-03 16:28:31 +0800
• 6000241b10
  Add Deepspeed Example of FLEX Mistral (#10640) Heyang Sun 2024-04-03 16:04:17 +0800