inkcherry
897e46b2fb
Merge branch 'main' into upstream_mori_
2025-11-27 15:35:35 +08:00
inkcherry
ad5678b056
format
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:32:21 +00:00
inkcherry
b3b195a540
update
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:59 +00:00
inkcherry
7d3a93f1e7
format
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:59 +00:00
inkcherry
63e6cff196
update proxy path
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:59 +00:00
inkcherry
77321502e7
update lock
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:59 +00:00
inkcherry
374cc25e0f
format
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:59 +00:00
inkcherry
16d2a7a343
updata finished request collection
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:59 +00:00
inkcherry
1c10f47dc6
tp write single pass
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:59 +00:00
inkcherry
b29f405aa5
update
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:59 +00:00
inkcherry
4776e2ddcf
more
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:59 +00:00
inkcherry
72ccb5d77c
remove handle_proxy_request
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:59 +00:00
inkcherry
38d51f6dd8
refine code
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:59 +00:00
inkcherry
fd63437837
update
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:58 +00:00
inkcherry
0a3ae0b0cc
update
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:58 +00:00
inkcherry
9d29f361fb
update
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:58 +00:00
inkcherry
96da87bfe0
refine
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:58 +00:00
inkcherry
857d93cbfb
fix all commit
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:58 +00:00
inkcherry
795a305b1b
fix format
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:58 +00:00
inkcherry
e0885e52d9
break long line
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:58 +00:00
inkcherry
f75eecde0a
fix all mypy
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:58 +00:00
inkcherry
3f7120368e
fix mypy and tp test pass
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:58 +00:00
inkcherry
4c79f34e8a
fix mypy
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:58 +00:00
inkcherry
9b90f5ddb2
update
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:58 +00:00
inkcherry
a0d74ebf7f
fix format error
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:58 +00:00
inkcherry
08cd2efbb6
refine
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:58 +00:00
inkcherry
bba4c89ca4
format
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:58 +00:00
inkcherry
4034937733
remove port
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:58 +00:00
inkcherry
b60ee86585
format
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:58 +00:00
inkcherry
4f592ae696
format
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:58 +00:00
inkcherry
245b71a891
refine
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:58 +00:00
inkcherry
64694c3e76
refine
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:58 +00:00
inkcherry
70ea1b2460
refine code
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:58 +00:00
inkcherry
68a2333339
fix dp proxy
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:58 +00:00
inkcherry
f8e9adfea8
refine
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:57 +00:00
inkcherry
ecbad2a70b
add proxy example
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:57 +00:00
inkcherry
e0f4336a5b
format
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:57 +00:00
inkcherry
675943e018
fix dp router
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:57 +00:00
inkcherry
a7ea23d16d
fix with new main branch
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:57 +00:00
inkcherry
b3e31b42d8
update gitignore
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:57 +00:00
inkcherry
9a15ae9f72
initial commit
...
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 07:30:57 +00:00
Johnny Yang
3ecabd06ee
Fix tpu-inference platform path ( #29554 )
...
Signed-off-by: Johnny Yang <johnnyyang@google.com>
2025-11-26 23:25:21 -08:00
Jee Jee Li
c069086b9c
[Bugfix] Fix getting device for MoE LoRA ( #29475 )
...
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-11-26 23:16:07 -08:00
Woosuk Kwon
11ea5ec1ff
[Model Runner V2] Refactor CudaGraphManager ( #29583 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-11-26 21:37:59 -08:00
Fadi Arafeh
ecb1952378
[cpu][fix] Fix Arm CI tests ( #29552 )
...
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
2025-11-27 13:09:41 +08:00
TJian
da8e1a1bf9
[DOC] Add vLLM Bangkok Meetup info ( #29561 )
...
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
2025-11-27 04:42:50 +00:00
Woosuk Kwon
ee80aee1ca
[Model Runner V2] Minor cleanup for build_attn_metadata ( #29576 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-11-26 20:10:12 -08:00
Woosuk Kwon
0aeb698b77
[Model Runner V2] Minor code cleanup ( #29570 )
...
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-11-26 19:47:17 -08:00
Louie Tsai
9bb33c8919
add xpu supported model and model id for cpu ( #29380 )
...
Signed-off-by: Tsai, Louie <louie.tsai@intel.com>
2025-11-27 11:30:50 +08:00
Jinzhen Lin
a67dec7cba
[Bugfix] fix IMA issue in certain cases of the moe marlin kernel ( #28619 )
...
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
2025-11-26 19:02:21 -08:00