jshixiong
|
792deda76f
|
fix: fix bug
|
4 months ago |
jshixiong
|
b011f9f83d
|
fix: fix bug
|
4 months ago |
jshixiong
|
4637079e4a
|
fix:test2
|
4 months ago |
jshixiong
|
51a650c17c
|
fix:test
|
4 months ago |
jshixiong
|
be05884b47
|
fix: update linux install
|
4 months ago |
jshixiong
|
01e0b8b5ae
|
fix:update poetry.lock
|
4 months ago |
gitlawr
|
8fe557148d
|
fix: qwen3-coder param
|
4 months ago |
gitlawr
|
dfdafd036d
|
docs: update huggingface_token config example
|
4 months ago |
yxf
|
26e81dc700
|
feat: Add support for Nvidia MIG detection in containerized environments.
|
4 months ago |
gitlawr
|
b24d08bbf1
|
chore: update auth config
|
4 months ago |
thxCode
|
f7636a5f63
|
ci(docker): lock ray version
Signed-off-by: thxCode <thxcode0824@gmail.com>
|
4 months ago |
thxCode
|
80509b5900
|
ci(docker/npu): fix different torch library
Signed-off-by: thxCode <thxcode0824@gmail.com>
|
4 months ago |
gitlawr
|
4535fb182d
|
docs: update sso cli flags
|
4 months ago |
gitlawr
|
e91da52145
|
feat: make JWT expiration configurable
|
4 months ago |
gitlawr
|
67b93d156e
|
feat: add user avatar
|
4 months ago |
gitlawr
|
30533f7275
|
feat: improve SSO
- Get OIDC endpoints from discovery
- Support POST method SAML ACS
- Simplify configurations
- Fix typos
- Update documentation
|
4 months ago |
gitlawr
|
e627a4c79e
|
fix: update pipx envs
|
4 months ago |
gitlawr
|
f7fdcdb9d0
|
chore: remove legacy models
|
4 months ago |
gitlawr
|
0d77f69e99
|
feat: add GLM4.5, Qwen3-Coder, Qwen3-2507 and gpt-oss models
|
4 months ago |
ZhouForrest
|
54d75c7a45
|
Add SSO Authentication (#2658)
* Add OIDC & SMAL SSO authentication
---------
Authored-by: forrestzhou <forrest@qq.com>
|
5 months ago |
thxCode
|
ea6e5ca9dc
|
ci(docker/cuda): fix failed on llama-box starting
Signed-off-by: thxCode <thxcode0824@gmail.com>
|
5 months ago |
yxf
|
df31850efc
|
fix: Enhance download log display logic
|
5 months ago |
yxf
|
67df35a364
|
fix: Update progress bar styling for frontend formatting compatibility.
|
5 months ago |
yxf
|
10eaab6f90
|
feat: Optimize dependency management for specified backend versions
|
5 months ago |
gitlawr
|
fac6ed8d25
|
chore: bump llama-box to v0.0.169
|
5 months ago |
thxCode
|
7e08098981
|
ci(docker/cpu): bump python version
Signed-off-by: thxCode <thxcode0824@gmail.com>
|
5 months ago |
thxCode
|
bf6287c069
|
ci(docker/npu): bump vllm version
Signed-off-by: thxCode <thxcode0824@gmail.com>
|
5 months ago |
thxCode
|
e54e269f58
|
ci(docker/cuda): build flashinfer from source
Signed-off-by: thxCode <thxcode0824@gmail.com>
|
5 months ago |
thxCode
|
5dd58c72cb
|
ci(docker): support git-lfs checkout
Signed-off-by: thxCode <thxcode0824@gmail.com>
|
5 months ago |
thxCode
|
a6441ff92e
|
ci(docker/dcu): refer base image from gpustack acr
Signed-off-by: thxCode <thxcode0824@gmail.com>
|
5 months ago |
thxCode
|
e2c0a7ccdc
|
ci(docker/corex): refer base image from gpustack acr
Signed-off-by: thxCode <thxcode0824@gmail.com>
|
5 months ago |
thxCode
|
cb14580408
|
ci(docker/npu): bump mindie version to 2.1.rc1
Signed-off-by: thxCode <thxcode0824@gmail.com>
|
5 months ago |
thxCode
|
359dc3c6e2
|
chore(docker): collect dockerfile together
Signed-off-by: thxCode <thxcode0824@gmail.com>
|
5 months ago |
linyinli
|
8ff76ebfee
|
docs: update wechat qrcode
Signed-off-by: linyinli <yinlin@gpustack.ai>
|
5 months ago |
linyinli
|
b5b2272e12
|
docs: update wechat qrcode
Signed-off-by: linyinli <yinlin@gpustack.ai>
|
5 months ago |
thxCode
|
53d255cba6
|
refactor(box): version candidate selecting
Signed-off-by: thxCode <thxcode0824@gmail.com>
|
5 months ago |
cyx
|
036c40753f
|
fix: proxy request fail when no reposnse within 300s
|
5 months ago |
yxf
|
7331059605
|
feat: Log the download progress in the model instance's log file.
|
5 months ago |
linyinli
|
5e22fe99ca
|
docs: update wechat qrcode
Signed-off-by: linyinli <yinlin@gpustack.ai>
|
5 months ago |
cyx
|
2232e4baf6
|
chore: update gguf-parser to 0.22.0
|
5 months ago |
Yuxing Deng
|
527f7b3644
|
fix: skip headers in proxy response
|
5 months ago |
gitlawr
|
35b570459b
|
chore: update cosyvoice huggingface repos
|
5 months ago |
yxf
|
a436eff8d3
|
fix: Fix potential division-by-zero exceptions.
|
5 months ago |
thxCode
|
6168713804
|
fix(ray): conflict in random runtime env agent port
Signed-off-by: thxCode <thxcode0824@gmail.com>
|
5 months ago |
Xiaodong Ye
|
309c27a9ef
|
llama-box: bump version
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
|
5 months ago |
gitlawr
|
307dadbbd5
|
ci: skip corex docker build
|
5 months ago |
yxf
|
74c937acc4
|
fix: Enhance multi-GPU scheduling tests and improve attention heads validation messages
|
5 months ago |
gitlawr
|
b0a638711b
|
fix: none distributed servers on upgrade
|
5 months ago |
cyx
|
14a60fd640
|
fix: the environment variable configuration "HTTP_PROXY HTTPS_PROXY" is invalid
|
5 months ago |
rushyrush
|
34c21e055f
|
fix: broken links in documentation
|
5 months ago |