Yina Chen
|
b6b70d1ba0
|
Divide core-xe packages (#11131)
* temp
* add batch
* fix style
* update package name
* fix style
* add workflow
* use temp version to run uts
* trigger performance test
* trigger win igpu perf
* revert workflow & setup
|
2024-05-28 12:00:18 +08:00 |
|
binbin Deng
|
c9168b85b7
|
Fix error during merging adapter (#11145)
|
2024-05-27 19:41:42 +08:00 |
|
Guancheng Fu
|
daf7b1cd56
|
[Docker] Fix image using two cards error (#11144)
* fix all
* done
|
2024-05-27 16:20:13 +08:00 |
|
binbin Deng
|
367de141f2
|
Fix mixtral-8x7b with transformers=4.37.0 (#11132)
|
2024-05-27 09:50:54 +08:00 |
|
Guancheng Fu
|
fabc395d0d
|
add langchain vllm interface (#11121)
* done
* fix
* fix
* add vllm
* add langchain vllm exampels
* add docs
* temp
|
2024-05-24 17:19:27 +08:00 |
|
ZehuaCao
|
63e95698eb
|
[LLM]Reopen autotp generate_stream (#11120)
* reopen autotp generate_stream
* fix style error
* update
|
2024-05-24 17:16:14 +08:00 |
|
Yishuo Wang
|
1dc680341b
|
fix phi-3-vision import (#11129)
|
2024-05-24 15:57:15 +08:00 |
|
Guancheng Fu
|
7f772c5a4f
|
Add half precision for fastchat models (#11130)
|
2024-05-24 15:41:14 +08:00 |
|
Zhao Changmin
|
65f4212f89
|
Fix qwen 14b run into register attention fwd (#11128)
* fix qwen 14b
|
2024-05-24 14:45:07 +08:00 |
|
Yishuo Wang
|
1db9d9a63b
|
optimize internlm2 xcomposer agin (#11124)
|
2024-05-24 13:44:52 +08:00 |
|
Yishuo Wang
|
9372ce87ce
|
fix internlm xcomposer2 fp16 (#11123)
|
2024-05-24 11:03:31 +08:00 |
|
Cengguang Zhang
|
011b9faa5c
|
LLM: unify baichuan2-13b alibi mask dtype with model dtype. (#11107)
* LLM: unify alibi mask dtype.
* fix comments.
|
2024-05-24 10:27:53 +08:00 |
|
Jiao Wang
|
0a06a6e1d4
|
Update tests for transformers 4.36 (#10858)
* update unit test
* update
* update
* update
* update
* update
* fix gpu attention test
* update
* update
* update
* update
* update
* update
* update example test
* replace replit code
* update
* update
* update
* update
* set safe_serialization false
* perf test
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* delete
* update
* update
* update
* update
* update
* update
* revert
* update
|
2024-05-24 10:26:38 +08:00 |
|
Xiangyu Tian
|
b3f6faa038
|
LLM: Add CPU vLLM entrypoint (#11083)
Add CPU vLLM entrypoint and update CPU vLLM serving example.
|
2024-05-24 09:16:59 +08:00 |
|
Yishuo Wang
|
797dbc48b8
|
fix phi-2 and phi-3 convert (#11116)
|
2024-05-23 17:37:37 +08:00 |
|
Yishuo Wang
|
37b98a531f
|
support running internlm xcomposer2 on gpu and add sdp optimization (#11115)
|
2024-05-23 17:26:24 +08:00 |
|
Zhao Changmin
|
c5e8b90c8d
|
Add Qwen register attention implemention (#11110)
* qwen_register
|
2024-05-23 17:17:45 +08:00 |
|
Yishuo Wang
|
0e53f20edb
|
support running internlm-xcomposer2 on cpu (#11111)
|
2024-05-23 16:36:09 +08:00 |
|
Yishuo Wang
|
cd4dff09ee
|
support phi-3 vision (#11101)
|
2024-05-22 17:43:50 +08:00 |
|
Xin Qiu
|
71bcd18f44
|
fix qwen vl (#11090)
|
2024-05-21 18:40:29 +08:00 |
|
Yishuo Wang
|
f00625f9a4
|
refactor qwen2 (#11087)
|
2024-05-21 16:53:42 +08:00 |
|
Yishuo Wang
|
d830a63bb7
|
refactor qwen (#11074)
|
2024-05-20 18:08:37 +08:00 |
|
Wang, Jian4
|
74950a152a
|
Fix tgi_api_server error file name (#11075)
|
2024-05-20 16:48:40 +08:00 |
|
Yishuo Wang
|
4e97047d70
|
fix baichuan2 13b fp16 (#11071)
|
2024-05-20 11:21:20 +08:00 |
|
Wang, Jian4
|
a2e1578fd9
|
Merge tgi_api_server to main (#11036)
* init
* fix style
* speculative can not use benchmark
* add tgi server readme
|
2024-05-20 09:15:03 +08:00 |
|
Yishuo Wang
|
31ce3e0c13
|
refactor baichuan2-13b (#11064)
|
2024-05-17 16:25:30 +08:00 |
|
Ruonan Wang
|
f1156e6b20
|
support gguf_q4k_m / gguf_q4k_s (#10887)
* initial commit
* UPDATE
* fix style
* fix style
* add gguf_q4k_s
* update comment
* fix
|
2024-05-17 14:30:09 +08:00 |
|
Yishuo Wang
|
981d668be6
|
refactor baichuan2-7b (#11062)
|
2024-05-17 13:01:34 +08:00 |
|
Ruonan Wang
|
3a72e5df8c
|
disable mlp fusion of fp6 on mtl (#11059)
|
2024-05-17 10:10:16 +08:00 |
|
SONG Ge
|
192ae35012
|
Add support for llama2 quantize_kv with transformers 4.38.0 (#11054)
* add support for llama2 quantize_kv with transformers 4.38.0
* fix code style
* fix code style
|
2024-05-16 22:23:39 +08:00 |
|
SONG Ge
|
16b2a418be
|
hotfix native_sdp ut (#11046)
* hotfix native_sdp
* update
|
2024-05-16 17:15:37 +08:00 |
|
Xin Qiu
|
6be70283b7
|
fix chatglm run error (#11045)
* fix chatglm
* update
* fix style
|
2024-05-16 15:39:18 +08:00 |
|
Yishuo Wang
|
8cae897643
|
use new rope in phi3 (#11047)
|
2024-05-16 15:12:35 +08:00 |
|
Yishuo Wang
|
59df750326
|
Use new sdp again (#11025)
|
2024-05-16 09:33:34 +08:00 |
|
SONG Ge
|
9942a4ba69
|
[WIP] Support llama2 with transformers==4.38.0 (#11024)
* support llama2 with transformers==4.38.0
* add supprot for quantize_qkv
* add original support for 4.38.0 now
* code style fix
|
2024-05-15 18:07:00 +08:00 |
|
Yina Chen
|
686f6038a8
|
Support fp6 save & load (#11034)
|
2024-05-15 17:52:02 +08:00 |
|
Ruonan Wang
|
ac384e0f45
|
add fp6 mlp fusion (#11032)
* add fp6 fusion
* add qkv fusion for fp6
* remove qkv first
|
2024-05-15 17:42:50 +08:00 |
|
Wang, Jian4
|
2084ebe4ee
|
Enable fastchat benchmark latency (#11017)
* enable fastchat benchmark
* add readme
* update readme
* update
|
2024-05-15 14:52:09 +08:00 |
|
hxsz1997
|
93d40ab127
|
Update lookahead strategy (#11021)
* update lookahead strategy
* remove lines
* fix python style check
|
2024-05-15 14:48:05 +08:00 |
|
Wang, Jian4
|
d9f71f1f53
|
Update benchmark util for example using (#11027)
* mv benchmark_util.py to utils/
* remove
* update
|
2024-05-15 14:16:35 +08:00 |
|
Yishuo Wang
|
fad1dbaf60
|
use sdp fp8 causal kernel (#11023)
|
2024-05-15 10:22:35 +08:00 |
|
Yishuo Wang
|
ee325e9cc9
|
fix phi3 (#11022)
|
2024-05-15 09:32:12 +08:00 |
|
Zhao Changmin
|
0a732bebe7
|
Add phi3 cached RotaryEmbedding (#11013)
* phi3cachedrotaryembed
* pep8
|
2024-05-15 08:16:43 +08:00 |
|
Yina Chen
|
893197434d
|
Add fp6 support on gpu (#11008)
* add fp6 support
* fix style
|
2024-05-14 16:31:44 +08:00 |
|
Zhao Changmin
|
b03c859278
|
Add phi3RMS (#10988)
* phi3RMS
|
2024-05-14 15:16:27 +08:00 |
|
Yishuo Wang
|
170e3d65e0
|
use new sdp and fp32 sdp (#11007)
|
2024-05-14 14:29:18 +08:00 |
|
Guancheng Fu
|
a465111cf4
|
Update README.md (#11003)
|
2024-05-13 16:44:48 +08:00 |
|
Guancheng Fu
|
74997a3ed1
|
Adding load_low_bit interface for ipex_llm_worker (#11000)
* initial implementation, need tests
* fix
* fix baichuan issue
* fix typo
|
2024-05-13 15:30:19 +08:00 |
|
Yishuo Wang
|
1b3c7a6928
|
remove phi3 empty cache (#10997)
|
2024-05-13 14:09:55 +08:00 |
|
Yishuo Wang
|
ad96f32ce0
|
optimize phi3 1st token performance (#10981)
|
2024-05-10 17:33:46 +08:00 |
|