Commit Graph
1709 Commits
Author SHA1 Message Date
Nick Hill 82553692b8 [KV Connector] Fix NIXL mamba state pairing for multi-slot block tables (#50153)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
2026-07-29 09:45:53 -07:00
Michael GoinandOpenAI Codex d6247d7173 [Spec Decode][Perf] Replicate DSpark Markov head across TP ranks (#49731)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
2026-07-29 11:43:51 -04:00
a0c092ee72 [BugFix] Fix num_output_placeholders preemption underflow (#48245)
Signed-off-by: Chris Eastwood <chris.eastwood@pwn4g3.dev>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Chris Eastwood <chris.eastwood@pwn4g3.dev>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
2026-07-29 06:41:54 -07:00
Taneem Ibrahim 43eaefba5a [ModelRunner V2] Enable sequence pooling for embedding and classification models (#48791)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
2026-07-29 06:30:45 -07:00
f51193b9ae [Kernel][Mamba] Fused-kernel support for align-mode DS-conv state migration with num_accepted_tokens > 1 (#49291)
Signed-off-by: Sungsoo Ha <sungsooh@nvidia.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
2026-07-29 18:54:52 +08:00
Chang GuoandCursor Agent 542a8fad6d [KV Offload] Move CPUOffloadingSpec onto SharedOffloadRegion (#50094)
Signed-off-by: Change72 <changg@nvidia.com>
Co-authored-by: Cursor Agent <cursor-agent@cursor.com>
2026-07-29 13:05:50 +03:00
Jared Wenmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>Cyrus Leung
32e657e689 [BugFix] eagle draft max position embeddings (#49343)
Signed-off-by: JaredforReal <w13431838023@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
2026-07-29 01:24:47 -07:00
Philip Pesic dc1be79031 Add CachePolicyFactory for pluggable/external eviction policies (#49114)
Signed-off-by: Philip Pesic <philippesic06@gmail.com>
2026-07-29 07:34:55 +03:00
Zach Zhu 58f9659397 [Frontend][Core] Standardize request error handling with VLLMError hierarchy (#49665)
Signed-off-by: Zach Zhu <zzqshu@126.com>
2026-07-29 04:20:40 +00:00
Nick HillandJared Wen f37f03db4a [KV Connector] Support NIXL P/D for hybrid MLA+SSM models (#49762)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Jared Wen <w13431838023@gmail.com>
2026-07-29 11:50:30 +08:00
Andreas Karatzas 7398a30d79 [ROCm][CI] Stabilize ngram and suffix correctness test (#50190)
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
2026-07-28 20:29:00 -06:00
Nick HillandJeff Ma 6fbbcf2151 [BugFix] Stop dummy runs from writing mamba state through stale block-table rows (#49757)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Signed-off-by: Jeff Ma <jeffjma@umich.edu>
Co-authored-by: Jeff Ma <jeffjma@umich.edu>
2026-07-29 01:09:41 +00:00
Kevin Glynn 56f31af62a [Bugfix] Fix /wake_up crash on hybrid models (Mamba/DeltaNet) (#41602)
Signed-off-by: Kevin Glynn <kevglynn@gmail.com>
2026-07-29 00:17:35 +00:00
Divakar Verma fe65aa6a97 [CI][NIXL] Fix flaky DP+EP test port conflict (#50171)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
2026-07-29 00:12:50 +00:00
liuzhenwei e7f6a39db8 [Test] Make EPD correctness tests configurable for XPU (#50110)
Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>
2026-07-29 07:47:48 +08:00
Nick HillandAndreas Karatzas 6453fc0b8c [Bugfix] Don't reuse engine core payload buffer while zmq is sending it (#50053)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
2026-07-28 16:09:28 +00:00
30217b0e80 [Bugfix][KV Offload][P2P] Scope serve state to fetch rounds (#49877)
Signed-off-by: Itay Etelis <itay.etelis@ibm.com>
Co-authored-by: Itay Etelis <itay.etelis@ibm.com>
Co-authored-by: Itay Etelis <Itay.etelis@gmail.com>
2026-07-28 18:01:55 +03:00
Nick Hill 0d0504b54c [Core] Warm up runner-owned Triton kernels before the first request (#49903) 2026-07-28 07:58:02 -07:00
Jonguk CheongandOpenAI Codex 1e81853afc [Bugfix][KV Offload] Keep Mamba block span unscaled under DCP (#49964)
Signed-off-by: Jonguk Cheong <jdal3031@snu.ac.kr>
Co-authored-by: OpenAI Codex <codex@openai.com>
2026-07-28 17:41:55 +03:00
b6cbba8bc8 [Bugfix][Kernel] Fix batch invariance in RMSNorm kernels by pinning block size (#48391)
Signed-off-by: oops-oom <73481342@qq.com>
Signed-off-by: oops-oom <liubin8905@vip.qq.com>
Co-authored-by: oops-oom <73481342@qq.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Shengqi Chen <harry-chen@outlook.com>
2026-07-28 22:24:02 +08:00
Nick HillandClaude Opus 4.8 94100b5915 [CI] Wire untethered test files into CI jobs (#49340)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-28 14:02:31 +00:00
Nick HillandClaude Fable 5 601fa9a74e [KV Connector] Support NIXL heterogeneous P/D block sizes for hybrid models (#49612)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-28 06:45:02 -07:00
Liangliang Maandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 88402a41c4 [Test] Skip ROCm AITER MLA prefill tests on non-ROCm platforms (#49945)
Signed-off-by: Liangliang-Ma <liangliang.ma@intel.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-07-28 16:26:49 +08:00
MINJUN GILandOpenAI Codex 52c3c4a42f [Bugfix][KV Offload][OBJ] Preserve job completion during cleanup (#49947)
Signed-off-by: MINJUN GIL <alswnsrlf12@naver.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
2026-07-28 07:10:52 +03:00
a8f296083f [KV Offload] Make compact secondary identity TP-independent (#49858)
Signed-off-by: Change72 <changg@nvidia.com>
Co-authored-by: GPT-5.6 Sol <noreply@openai.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
2026-07-28 07:10:20 +03:00
Varun Sundar RabindranathandVarun Sundar Rabindranath d18ed2304a [KV-offload][FS] : Batch store/load_block in C (#49152)
Signed-off-by: <>
Co-authored-by: Varun Sundar Rabindranath <varun-sundar-rabindranath@h100-01.nemg-001.lab.rdu2.dc.redhat.com>
2026-07-28 11:21:53 +08:00
Giancarlo Delfin 272abd5f48 [Tests][Spec Decode] Add gemma4 MTP acceptance rates test (#47920)
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
2026-07-27 16:15:54 -07:00
Rishi PuriandClaude Opus 4.8 fd10e8946d [Test] Regression test for hybrid-Mamba eagle cache-peek in Mooncake connector (#43559) (#48361)
Signed-off-by: Rishi Puri <riship@nvidia.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-27 19:03:58 +00:00
Matthew Bonanniandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> bf2b45b5d6 [Attention] Integrate FlashAttention 4 SM100 headdim 256 support (#42669)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-07-27 18:25:50 +00:00
Connor CarpenterandNick Hill e3c2fc3b3c [Rust Frontend][gRPC] Add server and model discovery (#49491)
Signed-off-by: Connor Carpenter <connorc@nvidia.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
2026-07-27 09:53:27 -07:00
Nicolò Lucchesi 2b465b2c42 [Misc][PD] Nixl cleanup get_backend_aware_kv_block_len and virtually_split_kv_in_blocks (#49988)
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
2026-07-27 18:51:37 +02:00
Nick Hillandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 59a6b0411d [Core] Fix internal LB load-balancing (#49204)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-07-27 14:00:46 +00:00
Ronen Schaffer 77cba0259f [KV Offloading] Per-request tier filtering with TierFilter/TierMatcher (#48123)
Signed-off-by: Ronen Schaffer <ronen.schaffer@ibm.com>
2026-07-27 13:29:57 +03:00
Andreas KaratzasandOpenAI Codex 394beb633b [Bugfix][ROCm] Use batch DMA for CPU KV cache loads (#49843)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
2026-07-27 02:18:01 -07:00
liuzhenwei afc94523c9 [XPU][CI] Use platform device in InputBatch V2 test (#49939)
Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>
2026-07-27 15:28:02 +08:00
Xiaochang WuandCopilot 8061dc26bd [Bugfix] Normalize sparse MLA warmup compression ratios (#49392)
Signed-off-by: Wu, Xiaochang <xiaochang.wu@intel.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-07-27 07:02:48 +00:00
Dao007foreverandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> d742856610 [3/N][Core][KV Connector] Support reliable partial-tail KV offload for sub-block prompts (#49502)
Signed-off-by: Dao Le <Dao007forever@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-07-26 23:22:17 -07:00
Andreas Karatzas 5f89a03dcb [CI] Explicitly tear down speculative decode runners (#49910)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-07-27 05:32:46 +00:00
JasonandOr Ozeri 53397fbfac [Bugfix][KV Offload][P2P] Fix EngineCore crash reconnecting to a reaped peer (#49823)
Signed-off-by: Jason Yao <wsyjh8@gmail.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
2026-07-27 08:07:00 +03:00
Walter Beller-Moralesandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> 8040ef2426 [Frontend] expose stream_interval as req sampling param (#49754)
Signed-off-by: walterbm <walter.beller.morales@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-07-27 11:30:37 +08:00
Andreas Karatzas ac87549cbd [CI][ROCm] Reduce V1 attention test runtime (#49916)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-07-27 11:12:45 +08:00
limeward ffc4f08c8e [Core][KV-transfer] MoRIIO: heterogeneous TP<->DP prefill/decode read routing (#46116)
Signed-off-by: Edwin Lim <edwin.lim@mangoboost.io>
2026-07-27 02:10:00 +00:00
Nick Hill 50aa830482 [BugFix][MRV2] Don't create dummy requests longer than max_model_len (#49751)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
2026-07-27 02:04:20 +00:00
da3a252fd1 [KVOffload][P2P] Generic P2P secondary tier: peer lookup and serving via ParentManager (#48021)
Signed-off-by: Liran Schour <lirans@il.ibm.com>
Signed-off-by: liranschour <liranschour@users.noreply.github.com>
Co-authored-by: Or Ozeri <or@ozery.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
2026-07-26 11:45:47 +03:00
Chang GuoandOpenAI Codex 7eca0e1a64 [KV Offload] Deduplicate replicated MLA KV in the shared CPU region (#48906)
Signed-off-by: Change72 <changg@nvidia.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
2026-07-26 08:22:30 +03:00
Jonguk CheongandOr Ozeri 7a29a3c54c [Bugfix][KV Offload] Namespace persistent cache by model runner (#49440)
Signed-off-by: Jonguk Cheong <jdal3031@snu.ac.kr>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
2026-07-26 08:21:52 +03:00
Rui YinandOr Ozeri d30b1ecd1b [Bugfix][KV Offloading] Defer request finalization until final store (#49671)
Signed-off-by: Rui Yin <2260891073@qq.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
2026-07-25 20:58:09 +00:00
0b0bd2b5f6 [Feature] Add fault tolerance framework (simplified) for DP+EP external LB deployments (#44428)
Signed-off-by: fangyuchu <fangyuchu@qq.com>
Signed-off-by: a798347923 <2645302020@qq.com>
Signed-off-by: TianZhuo <2770730562@qq.com>
Signed-off-by: a798347923 <39047817+a798347923@users.noreply.github.com>
Signed-off-by: 205150940 <112750056+205150940@users.noreply.github.com>
Signed-off-by: w00689259 <wangzhuo66@huawei.com>
Signed-off-by: zWaNg3 <37772915+zWaNg3@users.noreply.github.com>
Signed-off-by: zWaNg3 <389750525@qq.com>
Signed-off-by: yzchang-plus <1078477584@qq.com>
Signed-off-by: Jade Zheng <zheng.shoujian@outlook.com>
Co-authored-by: zWaNg3 <37772915+zWaNg3@users.noreply.github.com>
Co-authored-by: a798347923 <2645302020@qq.com>
Co-authored-by: TianZhuo <2770730562@qq.com>
Co-authored-by: 205150940 <112750056+205150940@users.noreply.github.com>
Co-authored-by: a798347923 <39047817+a798347923@users.noreply.github.com>
Co-authored-by: w00689259 <wangzhuo66@huawei.com>
Co-authored-by: zWaNg3 <389750525@qq.com>
Co-authored-by: yzchang-plus <1078477584@qq.com>
Co-authored-by: Jade Zheng <zheng.shoujian@outlook.com>
2026-07-25 11:49:09 -04:00
Harry MellorandClaude Opus 5 0b1a8bb1f6 [Bugfix][CI] Fix stale Mooncake lookup expectation broken by a merge race (#49802)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-25 03:10:26 -07:00
0ba2aa35a8 Stabilize GPU memory teardown between ROCm CI tests (#49242)
Signed-off-by: aarushjain29 <Aarushi.Jain2@amd.com>
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
2026-07-25 04:21:36 +00:00