|
|
efda08481b
|
minor
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-09-18 16:31:01 -07:00 |
|
|
|
82da219ff9
|
Implement topk_logprobs
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-09-18 16:29:38 -07:00 |
|
|
|
323a05b3c5
|
update
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-09-18 15:51:36 -07:00 |
|
|
|
a98eff0762
|
minor
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-09-18 15:21:30 -07:00 |
|
|
|
67d8c0c21b
|
fix
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-09-18 15:15:31 -07:00 |
|
|
|
2bb2cb13f4
|
revert
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-09-18 14:54:19 -07:00 |
|
|
|
e171e5bb67
|
merge
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-09-18 14:53:32 -07:00 |
|
|
|
8407fa02ed
|
fix
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-09-18 14:52:23 -07:00 |
|
|
|
82e591f7eb
|
remove
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-09-18 14:35:25 -07:00 |
|
|
|
330058f9b8
|
fix
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-09-18 14:30:29 -07:00 |
|
|
|
9fac6aa30b
|
[BugFix] Fix DeepGEMM warmup, no m.weight_scale_inv (#25206)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
|
2025-09-18 14:26:28 -07:00 |
|
|
|
aabfaa08cf
|
fix
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-09-18 14:14:03 -07:00 |
|
|
|
a53ad626d6
|
[KV offload][1b/N] rename offloading to kv_offload (#25191)
Signed-off-by: Or Ozeri <oro@il.ibm.com>
|
2025-09-18 20:53:52 +00:00 |
|
|
|
bc6463ac97
|
hash
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-09-18 13:49:52 -07:00 |
|
|
|
1c3dad22ff
|
[V0 Deprecation] Remove unused async_timeout.py (#25190)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-09-18 20:35:21 +00:00 |
|
|
|
a4962833f9
|
minor
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-09-18 13:20:37 -07:00 |
|
|
|
3f50030cc8
|
fix
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-09-18 13:11:46 -07:00 |
|
|
|
cbdb47dc01
|
working
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-09-18 13:10:35 -07:00 |
|
|
|
92f337faeb
|
minor
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-09-18 12:44:21 -07:00 |
|
|
|
d2a30a2d93
|
[Bug] Fix torch Compilation Cache Hit Error (#25093)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2025-09-18 12:38:37 -07:00 |
|
|
|
9050087250
|
update
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-09-18 12:37:29 -07:00 |
|
|
|
75fb112d80
|
[Bug] Fix returned_lse not Defined issue (#25106)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
|
2025-09-18 19:32:24 +00:00 |
|
|
|
38db529f66
|
[feat]: Create interface for model-specific M-RoPE (#24194)
Signed-off-by: AzizCode92 <azizbenothman76@gmail.com>
Signed-off-by: Aziz <azizbenothman76@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2025-09-18 19:18:56 +00:00 |
|
|
|
c1d83f2bae
|
merge
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-09-18 12:13:56 -07:00 |
|
|
|
064cac7bb7
|
[fix]: remove data type hardcoding from gptoss model implementation (#23807)
Signed-off-by: Nikhil Gupta <nikhil.gupta2@arm.com>
|
2025-09-18 18:15:23 +00:00 |
|
|
|
e19bce40a1
|
[V0 Deprecation] Remove AsyncLLMEngine (#25025)
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
|
2025-09-18 11:07:42 -07:00 |
|
|
|
505805b645
|
[KV offload][1/N] Introduce an offloading component (#19848)
Signed-off-by: Or Ozeri <oro@il.ibm.com>
|
2025-09-18 10:57:07 -07:00 |
|
|
|
bbdc0f2366
|
[ROCm][AITER][Bugfix] Switch AITER to use PIECEWISE_AND_FULL compilation (#25104)
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
|
2025-09-18 17:46:47 +00:00 |
|
|
|
dc34059360
|
[ROCm][CI/Build] Use ROCm7.0 as the base (#25178)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
|
2025-09-18 09:36:55 -07:00 |
|
|
|
c4cb0af98a
|
[spec decode] Fix MTP inference path for MiMo-7B model (#25136)
Signed-off-by: zixi-qi <qizixi@meta.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2025-09-18 09:12:19 -07:00 |
|
|
|
1c3b1634aa
|
[Misc] Add codeowner for Transformers backend (#25180)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-09-18 09:01:50 -07:00 |
|
|
|
2ea50e977a
|
Enable Allgather/ReduceScatter backend for NaiveAllToAll (#23964)
Signed-off-by: Shu Wang. <shuw@nvidia.com>
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Signed-off-by: Shu Wang <shuw@nvidia.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2025-09-18 15:52:58 +00:00 |
|
|
|
b419937c78
|
[Docs] Fix warnings in mkdocs build (continued) (#25163)
Signed-off-by: Zerohertz <ohg3417@gmail.com>
|
2025-09-18 08:23:26 -07:00 |
|
|
|
5f696c33b1
|
[New Model] Support BertForTokenClassification / Named Entity Recognition (NER) task (#24872)
Signed-off-by: wang.yuqi <noooop@126.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2025-09-18 23:22:01 +08:00 |
|
|
|
67244c86f0
|
feat(api): Return 503 on /health when engine is dead (#24897)
Signed-off-by: dongbo910220 <1275604947@qq.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2025-09-18 14:29:40 +00:00 |
|
|
|
072d7e53e5
|
[PERF] Add conv1d metadata to GDN attn (#25105)
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
|
2025-09-18 14:27:49 +00:00 |
|
|
|
01a583fea4
|
[Kernel] Decouple Tile Size from Block Size in Triton Unified Attention Kernel (#21197)
Signed-off-by: Jan van Lunteren <jvl@zurich.ibm.com>
|
2025-09-18 14:27:01 +00:00 |
|
|
|
bc19d75985
|
[Misc] Add kv-connector label (#25156)
Signed-off-by: NickLucche <nlucches@redhat.com>
|
2025-09-18 13:56:07 +00:00 |
|
|
|
fbd6523ac0
|
Refactor dense FP8 tensor/channel/block utils and add CT FP8 block (#21404)
|
2025-09-18 08:53:45 -04:00 |
|
|
|
470484a4f5
|
[Structured Output][Refactor] Move apply_grammar_bitmask() method from ModelRunner to structured output utils (#21999)
Signed-off-by: shen-shanshan <467638484@qq.com>
|
2025-09-18 20:44:31 +08:00 |
|
|
|
21da73343a
|
[Misc] Clean up flags in vllm bench serve (#25138)
Signed-off-by: Roger Wang <hey@rogerw.io>
|
2025-09-18 12:43:33 +00:00 |
|
|
|
66072b36db
|
[Bugfix][Mamba] - Fix Conv State Kernel FP32 Support (#24883)
Signed-off-by: asafg <39553475+Josephasafg@users.noreply.github.com>
|
2025-09-18 12:21:17 +00:00 |
|
|
|
3ed1ec4af2
|
Fix validate-config pre-commit check (#25157)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-09-18 12:06:28 +00:00 |
|
|
|
5a33ae9a3f
|
Fix forward reference warning in documentation (#25150)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-09-18 11:41:41 +00:00 |
|
|
|
c9ff9e6f0c
|
[Docs] add the parallel sampling usage in LLMEngine and AsyncLLM (#24222)
|
2025-09-18 04:37:08 -07:00 |
|
|
|
eaffe4486c
|
[Docs] Fix pooling-params doc references in openai_compatible_server.md (#24939)
|
2025-09-18 04:36:47 -07:00 |
|
|
|
8ed039d527
|
Move StructuredOutputsConfig from config/__init__.py to config/structured_outputs.py (#25153)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2025-09-18 11:24:27 +00:00 |
|
|
|
37970105fe
|
[Model] Improve Pooling Model (#25149)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
|
2025-09-18 11:04:21 +00:00 |
|
|
|
cc935fdd7e
|
[Frontend] Support setting logprobs to -1 (#25031)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
|
2025-09-18 10:34:42 +00:00 |
|
|
|
abdfcd4f3d
|
silu-v1: Fix EPS not being used during max-reduction (#25069)
Signed-off-by: elvircrn <elvircrn@gmail.com>
|
2025-09-18 10:25:12 +00:00 |
|