 Giancarlo Delfin
|
dec13a33b7
|
[Model Runner V2][Spec Decode] Add multi-layer MTP speculator (#48892)
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
|
2026-07-30 15:54:15 -07:00 |
|
|
+13
|
aeeb36b1f1
|
[New model] Kimi K3 (#50000)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Ziming Huang <zelda.huanghuang@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Isotr0py <mozf@inferact.ai>
Co-authored-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: Summer Yang <girasoleyang@gmail.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
Co-authored-by: Bowen Wang <abmfy@icloud.com>
Co-authored-by: gnovack <novackgm@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: xiaozhoupy <peiyuanzhou1994@gmail.com>
Co-authored-by: Roy Wang <yasong.wang@inferact.ai>
Co-authored-by: Jeff (Junze) Ma <93145857+majunze2001@users.noreply.github.com>
Co-authored-by: Codex <codex@openai.com>
Co-authored-by: Wei Zhao <51183510+wzhao18@users.noreply.github.com>
|
2026-07-30 03:49:58 -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 |
|
|
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 |
|
|
Nick Hill
|
0d0504b54c
|
[Core] Warm up runner-owned Triton kernels before the first request (#49903)
|
2026-07-28 07:58:02 -07:00 |
|
|
Li, Jiang
|
90245f4190
|
[Bugfix] Fix multi-modal support on CPU MRV2 (#50073)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
|
2026-07-28 06:09:48 +00:00 |
|
|
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 |
|
|
Wentao Ye
|
b5bcb3ce88
|
[Refactor] Remove dead code in multiple files (#49745)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-07-27 15:58:26 -04:00 |
|
|
Nick HillandWoosuk Kwon
|
8112b6c997
|
[MRV2] Always build attn metadata at capture time (#49364) (#49995)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Woosuk Kwon <woosuk@inferact.ai>
|
2026-07-27 17:25:17 +00:00 |
|
|
|
d2ca3002d9
|
[MRV2][Performance] Skip no-op FP32 logits materialization (#47711)
Signed-off-by: jesse <szxfml@gmail.com>
Signed-off-by: Song Zhixin <szxfml@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-07-27 15:31:36 +00:00 |
|
|
Nick HillandBenjamin Chislett
|
439f336212
|
[Core] Fix gpu<->cpu syncs in MRV2 mamba_hybrid.py (#49736)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com>
|
2026-07-27 02:41:27 +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 |
|
|
Nick HillandTaneem Ibrahim
|
fdaa0d9e59
|
[ModelRunner V2] Support encoder-only attention (#49331)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
Co-authored-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
|
2026-07-27 00:38:44 +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 |
|
|
Woosuk Kwon
|
213f681f81
|
Revert "[Perf][GLM-5.2] Blackwell decode optimizations" (#49768)
|
2026-07-24 16:04:59 -07:00 |
|
|
|
dd72658e7d
|
[Perf][GLM-5.2] Blackwell decode optimizations (#48597)
Signed-off-by: Peiyuan Zhou <peiyuanzhou1994@gmail.com>
Signed-off-by: zhou <zhou@zhoudeMacBook-Pro.local>
Signed-off-by: Stefan Koncarevic <stefan.koncarevic@amd.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Giancarlo Delfin <32987265+TheEpicDolphin@users.noreply.github.com>
Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: zhou <zhou@zhoudeMacBook-Pro.local>
Co-authored-by: stefankoncarevic <Stefan.Koncarevic@amd.com>
|
2026-07-23 21:36:27 -07:00 |
|
|
vllm-agentandvllm-agent CI bot
|
494845e79f
|
Revert "[MRV2] Always build attn metadata at capture time" (#49364) (#49451)
Co-authored-by: vllm-agent CI bot <ci-bot@vllm-agent.local>
|
2026-07-23 09:51:33 -07:00 |
|
|
Michael GoinandNick Hill
|
ac36a7a1e7
|
[MRV2][Spec Decode] Avoid rejection sampler OOM by chunking (#48630)
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-07-23 18:13:13 +08:00 |
|
|
Nick Hillandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
521aa80f71
|
[Core] Simplify KVBlockZeroer index tensor handling (#48399)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-07-23 18:12:46 +08:00 |
|
|
Woosuk Kwon
|
6049424b7e
|
[MRV2] Always build attn metadata at capture time (#49364)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
|
2026-07-21 19:27:16 -07:00 |
|
|
Michael GoinandCodex
|
a7d00ec051
|
[Bugfix] DFlash fc sized wrong when num_target_layers != num_hidden_layers (#48524)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-07-21 14:42:52 -07:00 |
|
|
Nick HillandClaude Opus 4.8
|
de6ec294ef
|
[Bugfix] Fix DSA crash under breakable piecewise cudagraphs (#49302)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-07-21 18:28:13 +01:00 |
|
|
Ilya MarkovandMarkov Ilya
|
f890e1dbe2
|
[BugFix] Set graph_pool_id before FULL CUDA graph capture in ModelRunner V2 (#48843)
Signed-off-by: Markov Ilya <markovilya19@gmail.com>
Co-authored-by: Markov Ilya <markovilya19@gmail.com>
|
2026-07-21 08:59:26 -04:00 |
|
|
|
6700813f86
|
[3/N][KV-Cache Layout Refactor] Standardize Mamba cache; drop get_transfer_cache_regions (#44456)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-07-21 09:16:15 +00:00 |
|
|
vllm-agentandvllm-agent
|
1134545b6f
|
Revert "[Sampler] Stop upcasting logits to fp32 in apply_sampling_params" (#48641) (#49033)
Co-authored-by: vllm-agent <vllm-agent@users.noreply.github.com>
|
2026-07-21 09:36:45 +01:00 |
|
|
Isotr0py
|
ea0e9c8f2e
|
[MRV2] Add encoder cache profiling implementation (#47985)
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
|
2026-07-20 20:18:14 -07:00 |
|
|
Fynn Schmitt-UlmsandMichael Goin
|
642076d26c
|
Support loading sample_from_anchor flag from speculators config (#48639)
Signed-off-by: Fynn Schmitt-Ulms <fschmitt@redhat.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2026-07-20 14:52:43 -07:00 |
|
|
|
4ec199b66a
|
[Bugfix][Spec-Decode] Populate draft seq_lens_cpu_upper_bound for spec-decode attention metadata (#44492)
Signed-off-by: Oxana Korzh <okorzh@amd.com>
Signed-off-by: okorzh-amd <okorzh-amd@users.noreply.github.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: okorzh-amd <okorzh-amd@users.noreply.github.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
|
2026-07-20 20:50:58 +00:00 |
|
|
|
b6ff8a2f50
|
[Core] Add MRV2 virtual-batch PCP for MLA (#46570)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
|
2026-07-19 02:53:15 +00:00 |
|
|
|
425c4eafb0
|
[Sampler] Stop upcasting logits to fp32 in apply_sampling_params (#48641)
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-07-17 18:15:20 -07:00 |
|
|
|
41ea2dd44a
|
[Bugfix][V1/V2] Fix prompt_logprobs to respect logprobs_mode (#47680)
Signed-off-by: Wojciech Wais <wojciech.wais@gmail.com>
Signed-off-by: Federico Kamelhar <209537060+fede-kamel@users.noreply.github.com>
Signed-off-by: Allen Shen <aoshen@inferact.ai>
Co-authored-by: Wojciech Wais <wojciech.wais@gmail.com>
Co-authored-by: Federico Kamelhar <209537060+fede-kamel@users.noreply.github.com>
|
2026-07-17 21:58:59 +01:00 |
|
|
wendadawenandTianyu Guo
|
69d4f5ef63
|
[Bugfix][Multimodal] Fix Qwen3-Omni use_audio_in_video with mixed image/video inputs (#46213)
Signed-off-by: wendadawen <wendadawen@qq.com>
Signed-off-by: Tianyu Guo <guoty9@mail2.sysu.edu.cn>
Co-authored-by: Tianyu Guo <guoty9@mail2.sysu.edu.cn>
|
2026-07-17 08:31:16 +00:00 |
|
|
|
251f7e478e
|
[Model] Add PW CUDA graph support for Inkling [2/N] (#48822)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Giancarlo Delfin <32987265+TheEpicDolphin@users.noreply.github.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Isotr0py <mozf@inferact.ai>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-07-16 10:28:56 -07:00 |
|
|
Michael GoinandClaude Opus 4.8
|
8bfd683901
|
[Spec Decode] Add kv_cache_dtype to speculative_config to control separately from target (#48787)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
|
2026-07-15 23:49:23 -06:00 |
|
|
Michael GoinandClaude Fable 5
|
ecf4aa5ce2
|
[Bugfix] Fix FlashInfer non-causal draft attention (DFlash/DSpark) on Blackwell (#48167)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-15 12:44:01 -07:00 |
|
|
Nick Hill
|
26587f9519
|
[BugFix][ModelRunner V2] Fix stale attn metadata in speculator prefill cudagraph capture (#48261)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-07-13 09:39:15 -07:00 |
|
|
|
fc1c548093
|
Runtime Draft Weight Update for Speculative Decoding (#46725)
Signed-off-by: vx120 <893600387@qq.com>
Signed-off-by: vx120 <57470515+vx120@users.noreply.github.com>
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: crp0128 <191679376@qq.com>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
|
2026-07-11 22:51:53 -07:00 |
|
|
Jiangyun ZhuandYifan Qiao
|
481e481be7
|
[2/N][Core] support partial prefix cache hit for hybrid model (#46384)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
|
2026-07-12 05:37:51 +00:00 |
|
|
Lucas Wilkinsonandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
04d553f390
|
[Misc] Use meta tensor for KV cache stride calculation (#47316)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-07-10 23:24:59 -04:00 |
|
|
Lucas Wilkinsonandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
9c18e90f6c
|
[BugFix] Fix packed HND KV cache reshape for FlashAttention (#47314)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-07-10 23:22:39 -04:00 |
|
|
Michael Goin
|
08dfd68610
|
[Model] Add LongCat-Flash-Lite (n-gram embedding) (#47857)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-07-10 07:17:50 -07:00 |
|
|
Nick HillandClaude Opus 4.8
|
ff8d3488f2
|
[Bugfix][MRV2] Reset num_accepted_tokens on add_request in all modes (#48132)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-07-09 18:17:11 +00:00 |
|
|
Lucas WilkinsonandCodex
|
e08a915146
|
[Bugfix] Preserve tensor causal metadata for grouped attention (#48135)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Codex <codex@openai.com>
|
2026-07-09 17:57:53 +00:00 |
|
|
|
85b3a7264b
|
[Bugfix][Model Runner V2] Order uniform decodes first so spec decodes aren't misclassified as prefills (#47381)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-07-09 14:26:27 +01:00 |
|
|
Benjamin ChislettandWentao Ye
|
1cd75b3dd4
|
[Bugfix] Fix race condition in KVBlockZeroer (#48085)
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Signed-off-by: Benjamin Chislett <chislett.ben@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2026-07-09 09:18:19 +00:00 |
|
|
Nick Hill
|
a5d19cbb95
|
[Core] Move MRV1 late_interaction_runner.py out of MRV2 subtree (#48014)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-07-08 18:30:11 +00:00 |
|
|
Michael GoinandClaude Opus 4.8
|
0d12618e98
|
[Spec Decode] Support hybrid (SWA + full attention) DFlash drafters (#47914)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-07-08 11:12:45 -04:00 |
|
|
Benjamin Chislett
|
7bd154375d
|
[Bugfix] Fix mamba+dflash for MRV2 (#47698)
|
2026-07-07 15:59:13 -04:00 |
|
|
Dakai AnandNick Hill
|
65dcde1695
|
[Bugfix] Fix PD disagg + MTP correctness for Qwen3.5(GDN) (#47466)
Signed-off-by: Dakai An <dakaian108@gmail.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-07-07 13:51:22 +00:00 |
|