iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
12,946 Commits 3 Branches 0 Tags
eb28e8068dd870283f1a4fe8251ed9254d6f477e
Commit Graph
181 Commits
Author SHA1 Message Date
Or Ozeri 2be765b68a [BugFix] scheduler: Fix ordering preserving of skipped requests (#32173) 
Signed-off-by: Or Ozeri <oro@il.ibm.com>
 2026-01-12 18:39:38 +00:00
Or Ozeri 028599739d [BugFix] scheduler: Fix resuming of preempted requests after async load (#31583) 
Signed-off-by: Or Ozeri <oro@il.ibm.com>
 2026-01-10 12:39:25 -08:00
Yifan Qiao cd4a95e3aa [Feat][Core] Support multiple KV cache groups in Hybrid KV Coordinator (#31707) 
Signed-off-by: Yifan Qiao <yifanqiao@berkeley.edu>
 2026-01-09 10:53:20 -08:00
Lumosis b634e619bb Decouple page_size_bytes calculation in AttentionSpec for TPU/RPA Compatibility. (#31635) 
Signed-off-by: Lihao Ran <imlihao.ran@gmail.com>
Signed-off-by: Lumosis <30372757+Lumosis@users.noreply.github.com>
 2026-01-08 09:00:07 +00:00
Nick Hill 32f4e4db00 [Cleanup] Remove deprecated fields from CachedRequestData class (#31734) 
Signed-off-by: njhill <nickhill123@gmail.com>
 2026-01-05 21:07:14 +00:00
Yifan QiaoandKuntaiDu 52bf066516 [Core][Hybrid allocator + connector] Support hybrid allocator + kv cache connector (#30166) 
Signed-off-by: Yifan Qiao <yifanqiao@berkeley.edu>
Co-authored-by: KuntaiDu <kuntai@uchicago.edu>
 2025-12-26 18:25:46 -08:00
Michael Goin 8ee90c83f8 Add --max-model-len auto to auto-fit context to available memory (#29431) 
Signed-off-by: mgoin <mgoin64@gmail.com>
 2025-12-23 21:37:14 -08:00
Chen ZhangandYifan Qiao 538e830caa [KVEvent] User request.block_hash for parent block_hash (#30544) 
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Signed-off-by: Yifan Qiao <yifanqiao@berkeley.edu>
Co-authored-by: Yifan Qiao <yifanqiao@berkeley.edu>
 2025-12-23 18:23:43 -08:00
Roger WangandSun Kim f5f51e5931 [Core][MM] Optimize encoder cache manager by operating with embeddings only (#30475) 
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Sun Kim <sunytokki@gmail.com>
 2025-12-16 14:18:17 -08:00
Or Ozeri 4c6fd25880 kv_transfer: Rename the shared storage connectors (#30201) 
Signed-off-by: Or Ozeri <oro@il.ibm.com>
 2025-12-08 20:46:09 -08:00
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
rasmithandRandall Smith feecba09af [CI/Build][AMD] Use float16 in test_reset_prefix_cache_e2e to avoid accuracy issues (#29997) 
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
 2025-12-05 08:42:25 +00:00
Mark McLoughlin 899e2ef558 [Core] Fix standalone runs of test_reset_prefix_cache_e2e (#29899) 
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
 2025-12-04 16:22:03 +08:00
ChaunceyandNick Hill 0a9caca9f5 [Bugfix] fix --scheduling-policy=priority & n>1 crashes engine (#29764) 
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
 2025-12-02 22:42:28 +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
Zhuohan LiandNick Hill d0cd728907 [Core] Support reseting all running requests' KV while calling reset_prefix_cache (#28827) 
Signed-off-by: Zhuohan Li <zhuohan123@gmail.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
 2025-12-02 02:25:05 +00:00
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
Marcin Ostrowski 5cfa967efa [Bugfix] TypeError: 'NoneType' object is not callable (#29414) 
Signed-off-by: Marcin Ostrowski <marcinx.ostrowski@intel.com>
 2025-12-01 13:16:44 +00:00
maang-h c7ba1f6bc7 [BugFix] Fix ValueError in NewRequestData repr methods (#29392) 
Signed-off-by: maang <maang_h@163.com>
 2025-11-28 13:42:30 +08:00
Yifan QiaoandChen Zhang 48ddb02b79 [Hybrid Allocator] Support KV cache groups with different block_size (#29143) 
Signed-off-by: Yifan Qiao <yifanqiao@berkeley.edu>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
 2025-11-25 10:30:57 -05:00
wang.yuqi 67fc16cd8c [Bugfix] If chunked_prefill is disabled, end the scheduling early. (#28911) 
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
 2025-11-25 16:06:09 +08:00
Chen Zhang 71df2a57ef [Hybrid Allocator] Better layer padding strategy for gpt-oss eagle (#29303) 
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
 2025-11-24 14:28:32 -08:00
Cyrus Leung 5a4802588e [Misc] Further clean up chunked prefill and prefix caching init (#29186) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-11-22 19:34:15 +08:00
Mark McLoughlinandNicolò Lucchesi c6fa3895e9 [KV Connector] Fix async connector prefix cache metrics (#28585) 
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
 2025-11-21 17:45:00 -05:00
Jialin Ouyang 30b9c67743 Revert "[Redo] #26368 (#28771)" (#29121) 
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
 2025-11-20 21:27:45 -08:00
Cyrus LeungandJialin Ouyang 98b4d389ed [Redo] #26368 (#28771) 
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
 2025-11-14 22:47:41 -08:00
Nick Hill ac86bff8cb Revert "[Core] Performance: Use list[np.ndarray] instead of list[list… (#28773) 2025-11-14 20:24:00 -08:00
Jialin Ouyang 186352b270 [Core] Performance: Use list[np.ndarray] instead of list[list[int]] for output tokens for GC optimization (#26368) 
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
 2025-11-14 16:04:04 -08:00
Marcin Ostrowski 0de4f217ab [Bugfix] TypeError: 'NoneType' object is not callable (#27410) 
Signed-off-by: Marcin Ostrowski <marcinx.ostrowski@intel.com>
 2025-11-14 21:13:53 +00:00
Cyrus Leung e2741f6cbc [Chore] Rename SchedulerConfig.chunked_prefill_enabled (#28735) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-11-14 18:39:57 +00:00
Cyrus Leung 511a6b611d [Config] Clean up SchedulerConfig initialization (#28665) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-11-14 22:41:02 +08:00
Mark McLoughlin 6e25b1cddf [KV Connector] Test async mode in scheduler tests (#28550) 
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
 2025-11-13 18:30:59 -05:00
Andy Lo 58ce8d12b7 [BugFix] Priority scheduling and spec tokens preemption (#28558) 
Signed-off-by: Andy Lo <andy@mistral.ai>
 2025-11-12 20:29:21 +00:00
Chenguang Zhengn00909098knlnguyen1802herotai214gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>Khuong LeKhuong Le
 		4ccffe561f [Core] Encoder separation for Encode-Prefill-Decode Disaggregation (#25233) 
Signed-off-by: n00909098 <nguyen.kha.long@huawei.com>
Signed-off-by: knlnguyen1802 <knlnguyen1802@gmail.com>
Signed-off-by: herotai214 <herotai214@gmail.com>
Signed-off-by: Khuong Le <khuong.le.manh@huawei.com>
Signed-off-by: Khuong Le <lemanhkhuong2611@gmail.com>
Co-authored-by: n00909098 <nguyen.kha.long@huawei.com>
Co-authored-by: knlnguyen1802 <knlnguyen1802@gmail.com>
Co-authored-by: herotai214 <herotai214@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Khuong Le <khuong.le.manh@huawei.com>
Co-authored-by: Khuong Le <lemanhkhuong2611@gmail.com>
 2025-11-11 18:58:33 -08:00
Kuntai Du 86dca07d9b [Hybrid allocator + kv connector] revert connector test changes related to hybrid allocator (#28011) 
Signed-off-by: KuntaiDu <kuntai@uchicago.edu>
 2025-11-05 10:36:31 +00:00
Nick Hill 938a81692e [AsyncScheduling] Don't schedule past request max_tokens (#27922) 
Signed-off-by: Nick Hill <nhill@redhat.com>
 2025-11-04 17:06:28 +00:00
Biswa Panda 1bf43ae35d [BugFix][LoRA] use adapter_id instead of id field of lora_request (#27728) 
Signed-off-by: Biswa Panda <biswa.panda@gmail.com>
 2025-11-03 10:08:08 +08:00
Nick Hill 0cdbe7b744 [Core] Async scheduling + structured outputs compatibility (#26866) 
Signed-off-by: Nick Hill <nhill@redhat.com>
 2025-11-01 00:35:04 +00:00
Kuntai Du b853540388 [Core][Hybrid allocator + kv connector 1/n] Enable hybrid allocator + KV cache connector (#25712) 
Signed-off-by: KuntaiDu <kuntai@uchicago.edu>
Signed-off-by: Kuntai Du <kuntai@uchicago.edu>
 2025-10-24 23:34:18 -07:00
Tova Movshovitz 88afa11010 [Metrics] [KVConnector] Add connector prefix cache hit rate stats (#26245) 
Signed-off-by: tovam <tovam@pliops.com>
 2025-10-23 12:21:08 +02:00
Andrew Sansom ff93cc8c84 [CORE] Support Prefix Caching with Prompt Embeds (#27219) 
Signed-off-by: Andrew Sansom <andrew@protopia.ai>
 2025-10-22 22:18:07 -07:00
Sage 1651003c35 [Prefix Cache] Use LoRA name for consistent KV-cache block hashing (#27211) 
Signed-off-by: Sage Ahrac <sagiahrak@gmail.com>
 2025-10-22 18:13:03 +00:00
dongbo910220 8a297115e2 [Chore] Separate out hashing utilities from vllm.utils (#27151) 
Signed-off-by: dongbo910220 <1275604947@qq.com>
 2025-10-19 11:09:38 +08:00
iAmir97iAmir97gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 		1d165d6d85 [Chore] Separate out vllm.utils.mem_utils (#27143) 
Signed-off-by: iAmir97 <Amir.balwel@embeddedllm.com>
Signed-off-by: iAmir97 <71513472+iAmir97@users.noreply.github.com>
Co-authored-by: iAmir97 <Amir.balwel@embeddedllm.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-10-18 10:06:59 +00:00
Tahsin TunanNick HillHarry Mellor
 		43721bc67f [CI] Replace large models with tiny alternatives in tests (#24057) 
Signed-off-by: Tahsin Tunan <tahsintunan@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-10-16 15:51:27 +01:00
Nick Hill 4aed506b65 [Core] Streamline some structured output related code (#26737) 
Signed-off-by: Nick Hill <nhill@redhat.com>
 2025-10-14 23:27:44 +00:00
Harry Mellor 8fcaaf6a16 Update Optional[x] -> x | None and Union[x, y] to x | y (#26633) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-10-12 09:51:31 -07:00
Harry Mellor 7c12763b24 Fix some typing issues found by mypy==1.18.2 (#26596) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-10-10 18:21:25 +00:00
Chen Zhang 606b00e80f [bugfix][DCP] fix block_size of hash in DCP prefix caching (#26296) 
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
 2025-10-10 03:02:49 -07:00