zR
|
9a27e77bba
|
requirement update
|
2024-08-11 17:59:00 +08:00 |
|
zR
|
913cb6dc06
|
部分依赖更新
|
2024-07-24 10:17:07 +08:00 |
ghohoj
|
f887394c02
|
fix: fix flow output when having tools
|
2024-07-22 10:17:09 +08:00 |
|
zR
|
4ab7a1efd1
|
依赖更新
|
2024-07-16 17:08:50 +08:00 |
|
zR
|
3dec01c6d5
|
dtype use bf16
|
2024-07-02 01:00:12 +08:00 |
jiawei
|
6c6d4637fb
|
Update README.md
|
2024-06-25 16:12:59 +08:00 |
|
zR
|
e5b5630498
|
fix #232
|
2024-06-24 23:45:04 +08:00 |
|
zR
|
5722878e25
|
update readme
|
2024-06-20 21:00:46 +08:00 |
|
zR
|
1de40b055f
|
update report
|
2024-06-20 11:33:05 +08:00 |
|
zR
|
b475ebe8ae
|
update finetune demo
|
2024-06-19 11:22:31 +08:00 |
|
zR
|
bab384d193
|
Merge pull request #155 from qq332982511/add_api_backend
composite demo add openai backend
|
2024-06-19 01:14:14 +08:00 |
|
zR
|
ab011a344e
|
add requirement of finetune
|
2024-06-19 01:12:20 +08:00 |
L
|
eb8aeb37c1
|
修正非流式输出和process_response tools参数的bug
|
2024-06-18 21:02:29 +08:00 |
|
zR
|
ef015f88f9
|
跟进OpenAI server部分代码解释
with liuzhenghua
|
2024-06-18 18:13:12 +08:00 |
|
zR
|
5c4bf6201c
|
fix openai stream function
|
2024-06-15 20:59:23 +08:00 |
黄乐乐
|
35ba249d28
|
Add GLM-4V-9B vision model gradio webui
|
2024-06-13 16:57:07 +08:00 |
yybear
|
293ca3b834
|
composite demo add openai backend
|
2024-06-12 23:59:22 +08:00 |
|
zR
|
adeeb0e8e0
|
Merge branch 'main' of https://github.com/THUDM/GLM-4
|
2024-06-09 16:11:23 +08:00 |
|
zR
|
a9fe1aba02
|
add openai demo stream and function call
fix #130 #124
|
2024-06-09 16:11:20 +08:00 |
|
zR
|
56426f2186
|
Merge pull request #91 from ztxtech/main
增加设置提示词的块
|
2024-06-08 20:18:57 +08:00 |
Tianxiang Zhan
|
8de4c76203
|
Update trans_web_demo.py
当设置prompt的时候跳过一轮
|
2024-06-08 16:39:07 +08:00 |
|
Tianxiang Zhan
|
76fff757b6
|
修正role
|
2024-06-08 16:12:58 +08:00 |
|
zR
|
20a9f26ec6
|
更新部分说明
|
2024-06-08 13:26:43 +08:00 |
|
zR
|
abe93e093d
|
openai demo update
#64 #36
|
2024-06-07 22:14:00 +08:00 |
|
zR
|
7fcaeba6cc
|
finetune and vision demo update
|
2024-06-07 16:53:56 +08:00 |
|
Tianxiang Zhan
|
f4fc0a316e
|
增加设置提示词的块
|
2024-06-06 19:57:58 +08:00 |
|
zR
|
9c2df689ac
|
Merge pull request #70 from T-Atlas/patch-1
Fix openai_api_server request_id issue
|
2024-06-06 17:35:09 +08:00 |
|
zR
|
ce2667cf5d
|
fix issue #74
|
2024-06-06 16:18:14 +08:00 |
|
zR
|
8102212b9f
|
fix with vllm requirements.txt
|
2024-06-06 13:57:22 +08:00 |
Lian Junhong
|
0b979f8bdb
|
Fix openai_api_server request_id issue
add request_id=f"{time.time()}" to Fix API concurrency request issue
|
2024-06-06 12:37:26 +08:00 |
|
zR
|
1683d673d2
|
fix #60 and #51
|
2024-06-06 10:14:15 +08:00 |
|
zR
|
3f26ccc208
|
fix readme error
|
2024-06-06 10:00:11 +08:00 |
|
zR
|
a263b69376
|
Merge pull request #28 from xusenlinzy/main
fix process response function
|
2024-06-05 18:07:07 +08:00 |
|
zR
|
0423d7ca6d
|
update link
|
2024-06-05 16:24:36 +08:00 |
xusenlin
|
11e244c0f2
|
fix process response function
|
2024-06-05 16:11:54 +08:00 |
|
zR
|
29480b7394
|
add vision demo
|
2024-06-05 13:21:23 +08:00 |
|
zR
|
12dd318013
|
add glm-4v-9b stress test
|
2024-06-05 12:55:41 +08:00 |
Lao
|
205b7db3cc
|
Update openai_api_server.py
Changed vllm’s gpu memory utilization
|
2024-06-05 11:48:20 +08:00 |
|
zR
|
d95f131b03
|
更新VLLM demo的参数
|
2024-06-05 11:43:08 +08:00 |
duzx16
|
c0a6d1e0fa
|
init commit
|
2024-06-05 10:22:16 +08:00 |