11747 Commits

Author SHA1 Message Date
inkcherry
ea9b6871f6 update
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
2025-11-27 11:50:41 +00:00
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