Michael Goin and GitHub
5e75a14a66
[Doc] Add DCP support to attention backend doc ( #33936 )
2026-02-09 18:33:43 -05:00
果冻虾仁 and GitHub
6f7adc533a
fix description in plugin_system.md ( #33999 )
2026-02-06 19:37:02 -08:00
Michael Goin and GitHub
c39ee9ee2b
[Docs] Add sections on process architecture and minimum CPU resources ( #33940 )
...
It seems users can be confused about vLLM's performance when running
with very small amounts of CPU cores available. We are missing a clear
overview of what vLLM's process architecture is, so I added this along with
some diagrams in arch_overview.md, and included a section on CPU resource
recommendations in optimization.md
Signed-off-by: mgoin <mgoin64@gmail.com >
2026-02-06 15:26:43 +00:00
Nicolò Lucchesi and GitHub
81a90e5277
[Docs] Add bart-plugin to docs ( #33905 )
...
Signed-off-by: NickLucche <nlucches@redhat.com >
2026-02-05 12:20:25 +00:00
Richard Zou and GitHub
fd9c83d0e0
[torch.compile] Document the workaround to standalone_compile failing ( #33571 )
...
Signed-off-by: Richard Zou <zou3519@gmail.com >
2026-02-03 07:16:55 +00:00
Cyrus Leung and GitHub
793af538a3
[Doc] Update plugin deprecation notices ( #33476 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2026-01-31 22:48:28 +08:00
jennyyyyzhen and GitHub
527bcd14d4
[ROCM] Enable aiter attn backend for qwen3-next model ( #32492 )
...
Signed-off-by: jennyyyyzhen <yzhen@hmc.edu >
2026-01-31 17:03:57 +08:00
31b25f6516
[Doc]: fixing multiple typos in diverse files ( #33256 )
...
Signed-off-by: Didier Durand <durand.didier@gmail.com >
Signed-off-by: Didier Durand <2927957+didier-durand@users.noreply.github.com >
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-01-29 16:52:03 +08:00
Matthew Bonanni and GitHub
77c4f45c6c
[7/N][Attention][Docs] Add documentation for attention backends ( #32477 )
...
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com >
2026-01-28 17:20:22 -05:00
Angela Yi and GitHub
fb7abfc1d0
[docs] Improve tlparse section ( #33211 )
...
Signed-off-by: angelayi <yiangela7@gmail.com >
2026-01-28 02:07:37 +00:00
Matthew Bonanni and GitHub
a608b4c6c2
[5/N][Attention] Finish eliminating vllm/attention folder ( #32064 )
...
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com >
2026-01-27 10:02:51 -05:00
5a93b9162b
[MoE Refactor] Integrate Naive Prepare Finalize into MK ( #32567 )
...
Signed-off-by: Robert Shaw <robshaw@redhat.com >
Signed-off-by: Amir Klein <203507526+amirkl94@users.noreply.github.com >
Co-authored-by: Robert Shaw <robshaw@redhat.com >
Co-authored-by: amirkl94 <203507526+amirkl94@users.noreply.github.com >
2026-01-27 01:28:02 +00:00
Alex Brooks and GitHub
9ac818a551
[Misc] HF Hub LoRA Resolver ( #20320 )
...
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com >
2026-01-26 13:56:32 +00:00
wang.yuqi and GitHub
328cbb2773
[Frontend][2/n] Make pooling entrypoints request schema consensus | ChatRequest ( #32574 )
...
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io >
2026-01-22 10:32:44 +00:00
whx and GitHub
1861ae8aae
[PluggableLayer][1/N] Define PluggableLayer (Fix ci) ( #32744 )
...
Signed-off-by: whx-sjtu <2952154980@qq.com >
2026-01-21 11:38:04 -05:00
Robert Shaw and GitHub
42135d6898
[MoE Refactor] Oracle Select FP8+NVFP4 Kernels In Priority ( #32414 )
2026-01-21 08:22:33 -05:00
Lucas Kabela and GitHub
c80f92c14d
[Documentation] Fix typo in docs/design/torch_compile_multimodal.md ( #32741 )
...
Signed-off-by: Lucas Kabela <lucaskabela@meta.com >
2026-01-20 23:54:20 -08:00
Robert Shaw and GitHub
c78ee240b3
Revert "[PluggableLayer][1/N] Define PluggableLayer" ( #32725 )
2026-01-21 00:21:06 +00:00
whx and GitHub
4ca62a0dbd
[PluggableLayer][1/N] Define PluggableLayer ( #32331 )
...
Signed-off-by: whx-sjtu <2952154980@qq.com >
2026-01-20 16:19:21 +00:00
bb9172030e
[Metrics] Complete removal of deprecated vllm:time_per_output_token_seconds metric ( #32661 )
...
This PR completes the removal of the deprecated vllm:time_per_output_token_seconds
metric that was deprecated in v0.11, hidden in v0.12, scheduled for removal in v0.13,
but delayed until v0.15.
Signed-off-by: carlory <baofa.fan@daocloud.io >
Co-authored-by: Claude Haiku 4.5 <noreply@anthropic.com >
2026-01-20 12:28:41 +00:00
73f2a81c75
docs: prefix caching seems quite outdated ( #28784 )
...
Signed-off-by: lon <114724657+longregen@users.noreply.github.com >
Signed-off-by: Russell Bryant <russell.bryant@gmail.com >
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Russell Bryant <russell.bryant@gmail.com >
2026-01-19 11:49:52 -08:00
4a6af8813f
[MoE Refactor] Move Test Impl into Test Dirs ( #32129 )
...
Signed-off-by: Robert Shaw <rshaw@neuralmagic.com >
Co-authored-by: Robert Shaw <rshaw@neuralmagic.com >
2026-01-18 12:16:59 +08:00
Cyrus Leung and GitHub
9ea07b41da
[1/N] Reorganize multimodal processing code ( #32327 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2026-01-14 15:25:31 +00:00
Andrew Bennett and GitHub
f243abc92d
Fix various typos found in docs ( #32212 )
...
Signed-off-by: Andrew Bennett <potatosaladx@meta.com >
2026-01-13 03:41:47 +00:00
Matthew Bonanni and GitHub
20228cb851
[3/N][Attention] Move AttentionMetadata-related code from utils.py to backend.py ( #32054 )
...
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com >
2026-01-12 09:13:56 -08:00
XlKsyt and GitHub
899541bdb1
[doc] fix broken links ( #32158 )
...
Signed-off-by: minimAluminiumalism <caixuesen@outlook.com >
2026-01-12 10:18:38 +00:00
Matthew Bonanni and GitHub
2612ba9285
[1/N][Attention] Restructure attention: move files ( #31916 )
...
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com >
2026-01-09 13:10:24 -08:00
Shanshan Shen and GitHub
08d954f036
[Doc] Add developer guide for CustomOp ( #30886 )
...
Signed-off-by: shen-shanshan <467638484@qq.com >
2026-01-09 16:21:11 +00:00
Lucas Kabela and GitHub
f16bfbe5bc
[Documentation][torch.compile] Add documentation for torch.compile + multimodal encoders ( #31627 )
...
Signed-off-by: Lucas Kabela <lucaskabela@meta.com >
2026-01-08 14:33:24 -05:00
9f6dcb71ae
[MoE Refactor][16/N] Apply Refactor to NVFP4 ( #31692 )
...
Signed-off-by: Robert Shaw <robshaw@redhat.com >
Signed-off-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com >
Co-authored-by: Robert Shaw <robshaw@redhat.com >
Co-authored-by: Michael Goin <mgoin64@gmail.com >
Co-authored-by: Pavani Majety <pmajety@nvidia.com >
2026-01-08 03:46:27 +00:00
Robert Shaw and GitHub
5dcd7ef1f2
[MoE Refactor][15/N] Apply Refactor to Fp8 ( #31415 )
2026-01-07 19:42:33 -05:00
weiyu and GitHub
e7596371a4
[Refactor][TPU] Remove torch_xla path and use tpu-inference ( #30808 )
...
Signed-off-by: Wei-Yu Lin <weiyulin@google.com >
Signed-off-by: weiyu <62784299+weiyu0824@users.noreply.github.com >
2026-01-07 16:07:16 +08:00
Cyrus Leung and GitHub
db318326a5
[Misc] Use deprecated for seed_everything ( #31780 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2026-01-06 11:29:55 +00:00
wangxiyuan and GitHub
bb4337b34c
[Platform] Deprecate seed_everything ( #31659 )
...
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com >
2026-01-04 18:34:04 -08:00
Harry Mellor and GitHub
decc244767
[Docs] Use relative md links instead of absolute html links for cross referencing ( #31494 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
2025-12-29 13:33:44 +00:00
Steve Westerhouse and GitHub
9d701e90d8
[Doc] Clarify FP8 KV cache computation workflow ( #31071 )
...
Signed-off-by: westers <steve.westerhouse@origami-analytics.com >
2025-12-22 08:41:37 +08:00
41b6f9200f
Remove all2all backend envvar ( #30363 )
...
Signed-off-by: Elizabeth Thomas <email2eliza@gmail.com >
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
2025-12-18 19:46:28 +00:00
rongfu.leng and GitHub
9e67c4ce98
[Docs] fix function name ( #30748 )
...
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io >
2025-12-17 12:14:45 +00:00
1a55cfafcb
[Doc]: fixing typos in various files ( #30540 )
...
Signed-off-by: Didier Durand <durand.didier@gmail.com >
Signed-off-by: Didier Durand <2927957+didier-durand@users.noreply.github.com >
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com >
2025-12-14 02:14:37 -08:00
Cyrus Leung and GitHub
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
2dcbac9077
[Docs] Generate full list of metrics in user docs ( #30388 )
...
Signed-off-by: Mark McLoughlin <markmc@redhat.com >
Co-authored-by: Claude <noreply@anthropic.com >
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
2025-12-10 16:09:34 +00:00
redwrasse and GitHub
6476382384
prefix caching design doc sha256 now default ( #29261 )
...
Signed-off-by: redwrasse <mail@redwrasse.io >
2025-12-06 07:39:56 +00:00
Yanan Cao and GitHub
62b3333448
[Frontend] Remove deprecated -O.xx flag ( #29991 )
...
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com >
2025-12-05 00:47:22 -08:00
TimWang and GitHub
690cc3ef20
docs: update metrics design doc to use new vllm:kv_cache_usage_perc ( #30041 )
...
Signed-off-by: Tim <tim.wang03@sap.com >
2025-12-04 23:37:14 +00:00
CYJiang and GitHub
fd68e909db
[docs] Remove _total from counter metrics names ( #30028 )
...
In Prometheus Counters always expose their actual numeric value with a metric name that ends in _total. We should document the base name, as this what appears in the get_metrics() API.
Signed-off-by: CYJiang <86391540+googs1025@users.noreply.github.com >
2025-12-04 07:46:15 +00:00
2902c34826
[Kernels] Remove BatchedTritonOrDeepGemmExperts and default fallback to Triton ( #29929 )
...
Signed-off-by: Bill Nell <bnell@redhat.com >
Signed-off-by: bnellnm <49004751+bnellnm@users.noreply.github.com >
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com >
2025-12-03 20:49:00 +00:00
2eb4fe9129
[examples] Resettle pooling examples. ( #29365 )
...
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io >
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
2025-12-02 15:54:28 +00:00
shivampr and GitHub
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
wang.yuqi and GitHub
62de4f4257
[Frontend] Resettle pooling entrypoints ( #29634 )
...
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io >
2025-12-01 15:30:43 +08:00
Cyrus Leung and GitHub
2afcec4dec
[Misc] Update TokenizerLike interface and move get_cached_tokenizer ( #29730 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2025-11-30 14:59:47 +08:00
