362 Commits

Author SHA1 Message Date
Jee Jee Li
421707dec1
Merge branch 'main' into mlm-full-lora-support 2025-12-12 15:00:59 +08:00
Jee Jee Li
208dc0c954 Fix comments
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-12-12 00:05:07 +00:00
Nicolò Lucchesi
0efd9f867c
[Core] Whisper Enable Encoder Batching (#29421)
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-12-11 21:06:51 +00:00
Harry Mellor
cf3eacfe58
Standardise get_rope to use rope_parameters["partial_rotary_factor"], not rotary_dim (#30389)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-12-11 20:45:23 +00:00
B-201
e10321bf6a
Merge branch 'main' into mlm-full-lora-support 2025-12-12 00:04:59 +08:00
bk-201
dd857e480f Merge branch 'mlm-full-lora-support' of https://github.com/jeejeelee/vllm into mlm-full-lora-support 2025-12-11 16:02:37 +00:00
Qiu
a11f4a81e0
[Misc][PCP&DCP] relocate PCP feature check (#30050)
Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
2025-12-11 03:36:18 -08:00
wang.yuqi
a5f9fb5960
[Deprecation] Deprecation --convert reward, use --convert embed instead. (#30463)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
2025-12-11 10:18:25 +00:00
bk-201
27448490f1 update argument name
Signed-off-by: bk-201 <joy25810@foxmail.com>
2025-12-11 06:46:53 +00:00
Cyrus Leung
7e24e5d4d6
[Deprecation] Remove deprecated task, seed and MM settings (#30397)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-12-10 19:59:39 -08:00
Cyrus Leung
5a87d8b9b1
[Deprecation] Remove deprecated plugin and compilation fields for v0.13 release (#30396)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-12-10 19:59:35 -08:00
B-201
d1307e1d29
Merge branch 'main' into mlm-full-lora-support 2025-12-11 11:47:50 +08:00
Will Eaton
a9e4106f28
[P/D] KV Load Failure Recovery/Abort Configuration (#26813)
Signed-off-by: Will Eaton <weaton@redhat.com>
Signed-off-by: Will Eaton <me@wseaton.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Mark McLoughlin <markmc@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
Co-authored-by: chaunceyjiang <chaunceyjiang@gmail.com>
2025-12-10 11:00:52 -08:00
Nicolò Lucchesi
c756fb6781
[Core] Whisper enable FULL_DECODE_ONLY CudaGraph (#30072)
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-12-10 06:14:24 -08:00
bk-201
5ff0c6fb73 Merge remote-tracking branch 'origin/main' into mlm-full-lora-support 2025-12-10 07:10:58 +00:00
PatrykSaffer
4c2e10ea19
[Bugfix] Fix cuda graph sizes when running with speculative decoding (#30330)
Signed-off-by: Patryk Saffer <patryk.saffer99@gmail.com>
Signed-off-by: PatrykSaffer <patryk.saffer@mistral.ai>
Co-authored-by: Patryk Saffer <patryk.saffer99@gmail.com>
2025-12-10 00:47:07 +00:00
Benjamin Chislett
e858bfe051
[Cleanup] Refactor profiling env vars into a CLI config (#29912)
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Signed-off-by: Benjamin Chislett <chislett.ben@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-12-09 13:29:33 -05:00
Laith Sakka
87aee9ed2b
Add evaluate_guards option to DynamicShapesConfig (#27432)
Signed-off-by: Laith Sakka <lsakka@meta.com>
2025-12-08 10:46:15 -05:00
wang.yuqi
9e77ffca3f
[Model][7/N] Improve all pooling task | Deprecation as_reward_model. Extract hidden states prefer using new multi-vector retrieval API (#26686)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
2025-12-08 08:10:09 +00:00
Isotr0py
b952f4d3c3
[v1] Add PrefixLM support to FlexAttention backend (#27938)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-12-07 15:51:36 +00:00
Cyrus Leung
e83b7e379c
Revert "[Renderer] Separate out RendererConfig from ModelConfig (#30145)" (#30199) 2025-12-07 00:00:22 -08:00
Cyrus Leung
27f4c2fd46
[Renderer] Separate out RendererConfig from ModelConfig (#30145)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-12-06 23:15:42 -08:00
Wentao Ye
17eb25e327
[Perf] Enable cuda graph for deepepHT, 5.3% throughput improvement, 4.4% TTFT improvement (#29558)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-12-07 04:44:50 +00:00
Nick Hill
4026ae31e9
[Misc] Move disable_nccl_for_dp_synchronization init logic into VllmConfig (#30161)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-12-05 20:59:04 -08:00
Rohan Potdar
40a046cd82
[Bugfix]: Fix TokenizerLike interface (#30009)
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
2025-12-05 20:56:40 -08:00
Harry Mellor
bf4a901af9
Better error when world size is larger than node and distributed_executor_backend is not set (#30140)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-12-05 20:53:52 -08:00
Bangsheng Tang
77e4472809
let draft model follow target model's config_format (#30152) 2025-12-05 13:33:42 -08:00
Ilya Markov
4e26d3b09e
[Compile] Conditional compilation. Introduce compile_ranges (#24252)
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Signed-off-by: ilmarkov <markovilya197@gmail.com>
Signed-off-by: Luka Govedič <luka.govedic@gmail.com>
Signed-off-by: ProExpertProg <lgovedic@redhat.com>
Co-authored-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Luka Govedič <luka.govedic@gmail.com>
2025-12-05 18:17:32 +00:00
Matthew Bonanni
66e674cdd5
[Attention][UX][1/N] Add AttentionConfig and change attention env vars to CLI arguments (#26315)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
2025-12-05 09:48:43 -08:00
Alec S
2c174420f5
Reduce validation to a warning (#28749)
Signed-off-by: Alec Solder <alecs@fb.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Alec Solder <alecs@fb.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-12-05 14:02:49 +00:00
B-201
1fbd7287b8
Merge branch 'main' into mlm-full-lora-support 2025-12-05 20:17:40 +08:00
bk-201
113eb2e0b8 add a enable option
Signed-off-by: bk-201 <joy25810@foxmail.com>
2025-12-05 12:14:53 +00:00
Max Hu
c2894d3883
[Feature] Add Layer-wise NVTX Support (#29990)
Signed-off-by: Max Hu <hyoung2991@gmail.com>
Signed-off-by: Max Hu <maxhu@nvidia.com>
Co-authored-by: Max Hu <maxhu@nvidia.com>
2025-12-05 11:20:07 +00:00
amitz-nv
6038b1b04b
[Frontend][Model] Add 'float16' to possible mamba cache dtype values, override mamba SSM cache dtype value for NemotronH (#29978)
Signed-off-by: amitz-nv <203509407+amitz-nv@users.noreply.github.com>
2025-12-05 00:34:33 -08:00
Qiu
0098a6e3da
[PCP&DCP] move CUDAGraph check for PCP&DCP to the check func of platforms (#29952)
Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
2025-12-04 21:40:51 -05:00
Mercykid-bash
1119f6e47a
Abstract eplb algo (#26471)
Signed-off-by: Che Ruan <cr623@ic.ac.uk>
Signed-off-by: mengxingkongzhouhan <117415539+mengxingkongzhouhan@users.noreply.github.com>
Signed-off-by: Mercykid-bash <ruanche0218@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Che Ruan <cr623@ic.ac.uk>
Co-authored-by: mengxingkongzhouhan <117415539+mengxingkongzhouhan@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-12-04 19:09:09 +00:00
wang.yuqi
74c4d80c6c
[Model][6/N] Improve all pooling task | Support chunked prefill with ALL pooling (#27145)
Signed-off-by: wang.yuqi <noooop@126.com>
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-12-04 13:44:15 +00:00
Arpit Khandelwal
dfdda96747
[Core] Remove forced None assignment for deprecated PassConfig flags (#29994)
Signed-off-by: arpitkh101 <arpit5khandelwal@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
2025-12-04 09:15:04 +00:00
Xieyang Xu
ad32e3e19c
enable multi-node in external launcher mode (#29833) 2025-12-03 17:02:02 -08:00
Lumis Chen
9bcf92295a
[Core] Add xxHash as a high-performance hash option for accelerating prefix caching (#29163)
Signed-off-by: LuminolT <lumischen01@gmail.com>
Signed-off-by: Lumis Chen <lumischen01@gmail.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>
2025-12-03 16:06:57 +00:00
Chauncey
b78772c433
[Frontend] supports deepseekv32 chat template (#29837)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
2025-12-03 20:53:44 +08:00
Yong Hoon Shin
69520bc695
Add logging for cudagraph related info (#29825)
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
2025-12-03 01:01:48 -08:00
Arpit Khandelwal
d7284a2604
[Core] Rename PassConfig flags as per RFC #27995 (#29646)
Signed-off-by: arpitkh101 <arpit5khandelwal@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
2025-12-03 03:38:55 +00:00
Isotr0py
63b1da76ba
[Chore]: Reorganize gguf utils funtions under transformers_utils (#29891)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-12-02 17:33:23 +00:00
Harry Mellor
951445a52d
Remove default values from InitVars so that they're not stored (#29859)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-12-02 12:16:37 +00:00
Julien Denize
d8c6210eea
Add Mistral Large 3 and Ministral 3 (#29757)
Signed-off-by: Julien Denize <julien.denize@mistral.ai>
Signed-off-by: Julien Denize <40604584+juliendenize@users.noreply.github.com>
Signed-off-by: Mickael Seznec <mickael@mistral.ai>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Mickael Seznec <mickael@mistral.ai>
2025-12-02 10:29:00 +00:00
Boyuan Feng
70fb77b4dc
[BugFix] add max-num-batched-token to scheduler hash (#29829)
Signed-off-by: Boyuan Feng <boyuan@meta.com>
2025-12-02 08:55:02 +00:00
Wei Wei
fc95521ba5
[Misc] Throw error on unintended access to scheduler_config.max_model_len (#29771)
Signed-off-by: Wei Wei <wwei6@meta.com>
2025-12-02 10:58:44 +08:00
Nengjun Ma
eaf81485ed
[Ascend]: Fixed the issue where OOT Platform vllm-ascend could not enable SP in Eager mode (#28935)
Signed-off-by: leo-pony <nengjunma@outlook.com>
2025-12-01 15:02:18 -05:00
shivampr
cabc77cc86
[Core][Observability] Add KV cache residency metrics (#27793)
Introduces three new Prometheus histograms for fine-grained observability of KV cache residency behavior:

vllm:kv_block_lifetime_seconds — total lifetime from allocation to free
vllm:kv_block_idle_before_evict_seconds — idle duration before eviction
vllm:kv_block_reuse_gap_seconds — time between consecutive reuses of the same block

These metrics help operators analyze KV cache efficiency, reuse patterns, and eviction timing beyond simple utilization rates.

Implementation uses monotonic timestamps for accuracy, 1% sampling for minimal overhead (~48 bytes/block), and is fully thread-safe with zero runtime cost when disabled.

Two new runtime flags are introduced:

--kv-cache-metrics – enable KV cache residency metrics
--kv-cache-metrics-sample – control sampling ratio (default: 0.01)

Signed-off-by: Shivam <shivamprasad91@gmail.com>
2025-12-01 18:27:53 +00:00