7935 Commits

Author SHA1 Message Date
Nick Hill
82f9292b84 infer hybrid lb mode on secondary modes
and update some comments

Signed-off-by: Nick Hill <nhill@redhat.com>
2025-07-22 13:24:34 +01:00
Nick Hill
36ed9f3467 fix coordinator for hybrid LB mode
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-07-22 13:17:42 +01:00
Nick Hill
60ae223986 Merge remote-tracking branch 'origin/main' into one-pod-per-node-lb
Signed-off-by: Nick Hill <nhill@redhat.com>

# Conflicts:
#	vllm/v1/engine/core_client.py
2025-07-21 19:20:59 +01:00
Michael Goin
005ae9be6c
Fix bad lm-eval fork (#21318) 2025-07-21 10:47:51 -07:00
Robert Shaw
29d1ffc5b4
[DP] Fix Prometheus Logging (#21257)
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
2025-07-21 09:11:35 -07:00
Lucas Wilkinson
304dce7ec0
[Attention] Clean up iRoPE in V1 (#21188)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
2025-07-21 09:10:30 -07:00
Ming Yang
6ece16c4fe
[Misc] Add dummy maverick test (#21199)
Signed-off-by: Ming Yang <minos.future@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-07-21 09:08:09 -07:00
simpx
a0e827e07c
[BugFix] make utils.current_stream thread-safety (#21252) (#21253)
Signed-off-by: simpx <simpxx@gmail.com>
2025-07-21 09:07:36 -07:00
Li, Jiang
a15a50fc17
[CPU] Enable shared-memory based pipeline parallel for CPU backend (#21289)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
2025-07-21 09:07:08 -07:00
Woosuk Kwon
6dda13c86b
[Misc] Add sliding window to flashinfer test (#21282)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-07-21 08:37:49 -07:00
Nick Hill
7a793ad562 fix data_parallel_hybrid_lb arg default value
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-07-21 15:29:48 +01:00
Zhiyu
6b46c4b653
Add Nvidia ModelOpt config adaptation (#19815)
Signed-off-by: Zhiyu Cheng <zhiyuc@nvidia.com>
2025-07-21 10:02:58 -04:00
Robert Shaw
58e4227fec
Update vllm/engine/arg_utils.py
Co-authored-by: Nick Hill <nhill@redhat.com>
2025-07-21 08:24:34 -04:00
Ning Xie
d97841078b
[Misc] unify variable for LLM instance (#20996)
Signed-off-by: Andy Xie <andy.xning@gmail.com>
2025-07-21 12:18:33 +01:00
Harry Mellor
e6b90a2805
[Docs] Make tables more space efficient in supported_models.md (#21291)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-07-21 02:25:02 -07:00
Harry Mellor
be54a951a3
[Docs] Fix hardcoded links in docs (#21287)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-07-21 02:23:57 -07:00
Cyrus Leung
042af0c8d3
[Model][1/N] Support multiple poolers at model level (#21227)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-07-21 02:22:21 -07:00
Cyrus Leung
378d33c392
[Bugfix] Fix missing placeholder in logger debug (#21280)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-07-20 22:50:06 -07:00
Huy Do
940af1f03a
Add the instruction to run e2e validation manually before release (#21023)
Signed-off-by: Huy Do <huydhn@gmail.com>
2025-07-20 22:29:18 -07:00
Simon Mo
92615d7fe8
[Docs] Add RFC Meeting to Issue Template (#21279)
Signed-off-by: simon-mo <simon.mo@hey.com>
2025-07-20 21:58:07 -07:00
Kay Yan
8188196a1c
[CI] Cleanup modelscope version constraint in Dockerfile (#21243)
Signed-off-by: Kay Yan <kay.yan@daocloud.io>
2025-07-20 20:13:02 -07:00
Robert Shaw
40397e378d finished validating
Signed-off-by: Robert Shaw <robshaw@redhat.com>
2025-07-21 00:46:31 +00:00
Robert Shaw
1b481d3489 updated
Signed-off-by: Robert Shaw <robshaw@redhat.com>
2025-07-21 00:33:24 +00:00
Robert Shaw
e80c015d24 updated
Signed-off-by: Robert Shaw <robshaw@redhat.com>
2025-07-21 00:29:18 +00:00
Robert Shaw
f53166a963 update ux
Signed-off-by: Robert Shaw <robshaw@redhat.com>
2025-07-21 00:21:35 +00:00
Robert Shaw
6feb4569fe update ux
Signed-off-by: Robert Shaw <robshaw@redhat.com>
2025-07-21 00:21:12 +00:00
Robert Shaw
5f0663bce4 cleanup
Signed-off-by: Robert Shaw <robshaw@redhat.com>
2025-07-21 00:08:26 +00:00
Robert Shaw
1dcd90065d updated
Signed-off-by: Robert Shaw <robshaw@redhat.com>
2025-07-21 00:00:40 +00:00
Robert Shaw
e81c277e6e updated
Signed-off-by: Robert Shaw <robshaw@redhat.com>
2025-07-20 23:55:02 +00:00
Robert Shaw
a58892880e updated
Signed-off-by: Robert Shaw <robshaw@redhat.com>
2025-07-20 23:53:10 +00:00
Robert Shaw
3c206b1975 updated
Signed-off-by: Robert Shaw <robshaw@redhat.com>
2025-07-20 23:52:07 +00:00
Robert Shaw
ec86e797da updated
Signed-off-by: Robert Shaw <robshaw@redhat.com>
2025-07-20 23:32:49 +00:00
Robert Shaw
d327a6bed5 cleanup
Signed-off-by: Robert Shaw <robshaw@redhat.com>
2025-07-20 23:26:48 +00:00
Robert Shaw
2d32c2849f stash
Signed-off-by: Robert Shaw <robshaw@redhat.com>
2025-07-20 23:10:16 +00:00
Robert Shaw
fe68027a08 updated
Signed-off-by: Robert Shaw <robshaw@redhat.com>
2025-07-20 22:45:45 +00:00
Robert Shaw
32a35f5d93 stash
Signed-off-by: Robert Shaw <robshaw@redhat.com>
2025-07-20 22:43:08 +00:00
Robert Shaw
be03d841f6 stash
Signed-off-by: Robert Shaw <robshaw@redhat.com>
2025-07-20 22:33:17 +00:00
Robert Shaw
91608889a4 updated
Signed-off-by: Robert Shaw <robshaw@redhat.com>
2025-07-20 22:19:37 +00:00
Robert Shaw
9f7d3217dd stash
Signed-off-by: Robert Shaw <robshaw@redhat.com>
2025-07-20 21:23:02 +00:00
Robert Shaw
85cd2da6b4 seems to be working again, but LB is wrong
Signed-off-by: Robert Shaw <robshaw@redhat.com>
2025-07-20 21:15:36 +00:00
Robert Shaw
a46bc0a6a3 updated
Signed-off-by: Robert Shaw <robshaw@redhat.com>
2025-07-20 21:06:47 +00:00
Robert Shaw
0018dd01c9 debug
Signed-off-by: Robert Shaw <robshaw@redhat.com>
2025-07-20 20:52:40 +00:00
Robert Shaw
093b9380db updated
Signed-off-by: Robert Shaw <robshaw@redhat.com>
2025-07-20 20:41:36 +00:00
Robert Shaw
cae7cb0223 updated
Signed-off-by: Robert Shaw <robshaw@redhat.com>
2025-07-20 20:36:47 +00:00
Robert Shaw
7127d838d7 updated
Signed-off-by: Robert Shaw <robshaw@redhat.com>
2025-07-20 20:34:58 +00:00
Robert Shaw
6491d59202 cleanup
Signed-off-by: Robert Shaw <robshaw@redhat.com>
2025-07-20 20:32:02 +00:00
Robert Shaw
fc79d23d9a updated
Signed-off-by: Robert Shaw <robshaw@redhat.com>
2025-07-20 20:24:10 +00:00
Robert Shaw
ad34f4a953 updated
Signed-off-by: Robert Shaw <robshaw@redhat.com>
2025-07-20 20:22:47 +00:00
Robert Shaw
99583c2a25 updated
Signed-off-by: Robert Shaw <robshaw@redhat.com>
2025-07-20 20:21:33 +00:00
Robert Shaw
2cf8ff64c7 updated
Signed-off-by: Robert Shaw <robshaw@redhat.com>
2025-07-20 20:17:54 +00:00