Commit Graph
99 Commits
Author SHA1 Message Date
Lucas Wilkinson de71747655 [SpecDecode] Simplified alternative padded-speculation acceptance rate fix (#29845)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
2025-12-22 13:06:10 -08:00
Andreas Karatzas 72aaac5b66 [ROCm][Bugfix] Add MLACommonMetadata to allowed attention types for speculative decoding (#30430)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2025-12-11 19:25:01 +00:00
Lucas WilkinsonandBenjamin Chislett abe93bce59 [Attention] Make seq_lens_cpu optional in CommonAttentionMetadata to enable true async spec-decode (#29624)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com>
2025-12-09 17:18:10 -08:00
Lucas Wilkinson 56037dfa2f [BugFix] Fix assert batch_descriptor.num_tokens == num_tokens_padded (#30173)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
2025-12-09 10:36:12 -05:00
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
Lucas Wilkinson c8ab988b15 [BugFix] Fix DBO assert assert B_block_table == B_q (#29933)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
2025-12-04 14:48:54 -05:00
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
Cyrus Leung 64bc09ba27 [Core] Enable inputs_embeds_size separate from hidden_size (#29741)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-11-30 17:31:12 +08:00
Benjamin Chislett 1986de1375 [Perf] Optimize EAGLE prepare_inputs_padded with triton kernels (#28597)
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Signed-off-by: Benjamin Chislett <chislett.ben@gmail.com>
2025-11-28 22:25:05 +00:00
37b15e97e8 [Multimodal][Speculative Decoding]Eagle3 mm support, enablement on qwen3vl (#29594)
Signed-off-by: Tsai, Louie <louie.tsai@intel.com>
Signed-off-by: EanWang211123 <wangyiheng@sangfor.com.cn>
Co-authored-by: Louie Tsai <louie.tsai@intel.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2025-11-27 22:05:45 -08:00
Matthew Bonanni fc1d8be3dc [Attention] Update attention imports (#29540)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
2025-11-27 11:19:09 -05:00
Eldar Kurtić 0231ce836a Revert back to torch.equal over torch.allclose from #28819 (#29086)
Signed-off-by: Eldar Kurtic <8884008+eldarkurtic@users.noreply.github.com>
2025-11-25 14:23:38 +00:00
Rémi Delacourt 12c007e288 EAGLE Support DP>1 (#26086)
Signed-off-by: Rémi Delacourt <remi@mistral.ai>
Signed-off-by: Rémi Delacourt <54138269+Flechman@users.noreply.github.com>
Signed-off-by: remi <remi@mistral.ai>
2025-11-25 07:32:21 +00:00
Hanjie QiuandBenjamin Chislett 5f9679a43b [Spec Decode] Add support for EAGLE3 heads that do not use_aux_hidden_states (#27688)
Signed-off-by: hjjq <hanjieq@nvidia.com>
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com>
2025-11-24 20:13:12 -05:00
Lucas Wilkinson 30d6466238 [BugFix] Fix Eagle IndexError: list index out of range for even num_speculative_tokens (#29102)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
2025-11-22 00:47:05 +00:00
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
Zhewen Li 93c8672ceb [Bugfix] Fix spec decode memory regression after #28549 (#28819)
Signed-off-by: zhewenli <zhewenli@meta.com>
2025-11-20 19:05:50 +08:00
Izzy PuttermanandCyrus Leung 02f5903b84 Eagle: MM Cuda Graphs with MRope (#28896)
Signed-off-by: Izzy Putterman <iputterman@nvidia.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
2025-11-19 15:01:05 -05:00
d8874c61a5 [Core] Async Scheduling X Spec Decoding Compatibility (#24799)
Signed-off-by: Ronald1995 <ronaldautomobile@163.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: Benjamin Chislett <chislett.ben@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com>
2025-11-17 12:16:20 -08:00
Eldar Kurtić e439c784fa Add support for Eagle with separate lm-head and embed_tokens layers (#28549)
Signed-off-by: Eldar Kurtic <8884008+eldarkurtic@users.noreply.github.com>
2025-11-15 06:12:02 -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
Harry Mellor 97d1c99302 Rename clashing method names for vLLM model protocol (#27583)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-11-12 19:14:33 -08:00
Matthew BonanniandLuka Govedič b30dfa03c5 [Attention] Refactor CUDA attention backend selection logic (#24794)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
2025-11-11 07:40:44 -05:00
yt0428andJee Jee Li 05cae69f0f [model] Add support for openPangu_Ultra_MoE (#27521)
Signed-off-by: yuantao <2422264527@qq.com>
Signed-off-by: yt0428 <51468697+yt0428@users.noreply.github.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
2025-11-04 08:17:20 -08:00
Haco d811b442d3 [Bugfix] DeepSeek V3.2 MTP metadata & CUDA graph issues (#26779)
Signed-off-by: xiaohajiayou <923390377@qq.com>
2025-11-01 10:52:43 -04:00
284cc92275 [MISC] cudagraph_capture_sizes related improvements (#26016)
Signed-off-by: fhl <2410591650@qq.com>
Signed-off-by: fhl2000 <63384265+fhl2000@users.noreply.github.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-10-24 05:11:05 -07:00
Jonathan Chen ca76486a16 [Chore] Separate out vllm.utils.platform_utils.py (#27374)
Signed-off-by: Jonathan <chenleejonathan@gmail.com>
2025-10-23 19:08:06 +00:00
Nicolò Lucchesi b26b70bec4 [Misc] Refactor get_kv_cache_spec into AttentionLayerBase (#26587)
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-10-18 13:51:21 +00:00
Pradyun92andPradyun Ramadorai acedc74b1a [V1][Spec Decode] Fix greedy temperature detection after sampler refactor (#27077)
Signed-off-by: Pradyun Ramadorai <pradyunr@amazon.com>
Co-authored-by: Pradyun Ramadorai <pradyunr@amazon.com>
2025-10-17 13:27:47 -07:00
Morrison TurnanskyandLuka Govedič 96b9aa5aa0 [Frontend][torch.compile] CompilationConfig Overhaul (#20283): name change compilation level to compilation mode, deprecation compilation level (#26355)
Signed-off-by: morrison-turnansky <mturnans@redhat.com>
Signed-off-by: Morrison Turnansky <mturnans@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
2025-10-15 02:51:16 +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
Vadim Gimpelson e94cfd51da [BUG] Qwen3-next MTP. Fix attn metadata build bug (#26564)
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
2025-10-10 14:59:03 -04:00
Lucas WilkinsonandBenjamin Chislett 29255cfc3b [Spec-Decode] Support piecewise cudagraphs for Eagle head (#25109)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com>
2025-10-10 01:20:31 -04:00
Ming Yang 3b736e1c38 [Attention][DCP] Support DCP with query length > 1 (MTP) with FA3 (#25049)
Signed-off-by: Ming Yang <minos.future@gmail.com>
2025-10-09 08:06:29 -07:00
Naveenraj KamalakannanandLuka Govedič e614ab7806 Separate MLAAttention class from Attention (#25103)
Signed-off-by: Naveenraj Kamalakannan <therealnaveenkamal@gmail.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
2025-10-08 17:11:11 -07:00
7mileandBenjamin Chislett b2ea5ba677 [Bugfix][Spec Decode] Fix wrong valid_mask for padded speculation when chunked prefill occurs (#26231)
Signed-off-by: seven-mile <i@7li.moe>
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com>
2025-10-06 18:24:22 +00:00
Harry Mellor d6953beb91 Convert formatting to use ruff instead of yapf + isort (#26247)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-10-05 07:06:22 -07:00
Lucia Fang 001e50c92c [Model] MTP fallback to eager for DeepSeek v32 (#25982)
Signed-off-by: Lu Fang <fanglu@fb.com>
2025-10-01 01:53:22 +00:00
+6 fa7e254a7f [New Model] DeepSeek-V3.2 (Rebased to Main) (#25896)
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Signed-off-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>
Signed-off-by: Lucia Fang <fanglu@meta.com>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Lucia Fang <116399278+luccafong@users.noreply.github.com>
Co-authored-by: Lucia Fang <fanglu@meta.com>
Co-authored-by: NickLucche <nlucches@redhat.com>
Co-authored-by: Siyuan Fu <siyuanf@nvidia.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Xiaozhu Meng <mxz297@gmail.com>
Co-authored-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>
2025-09-30 17:14:41 +08:00
Kunshang Ji 143844fa43 [XPU]Fix xpu spec decoding UTs, avoid using cuda graph (#25847)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
2025-09-29 05:15:10 +00:00
27d7638b94 [Bugfix] Merge MM embeddings by index instead of token IDs (#16229)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: NickLucche <nlucches@redhat.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
2025-09-27 08:15:12 +00:00
f1d53d150c [Multimodal][Speculative Decoding]Eagle Eagle3 mm support, enablement on qwen2.5vl (#22872)
Signed-off-by: Junhong <liujunhong11@huawei.com>
Signed-off-by: Junhong Liu <98734602+LJH-LBJ@users.noreply.github.com>
Co-authored-by: Junhong <liujunhong11@huawei.com>
Co-authored-by: LJH-LBJ <98734602+LJH-LBJ@users.noreply.github.com>
2025-09-27 03:35:47 +00:00
Jonas M. Kübler 6f5c0931c1 [Spec decode] automatically disable mm for text-only draft models (#25667)
Signed-off-by: Jonas Kuebler <kuebj@amazon.com>
2025-09-27 08:10:21 +08:00
qizixi c70ac4b8ff [spec decode] Consolidate speculative decode method name for MTP (#25232)
Signed-off-by: zixi-qi <qizixi@meta.com>
2025-09-26 22:27:05 +00:00
XuruiYangandyangxurui 845adb3ec6 [Model] Add LongCat-Flash (#23991)
Signed-off-by: yangxurui <yangxurui@meituan.com>
Co-authored-by: yangxurui <yangxurui@meituan.com>
2025-09-24 21:53:40 -07:00
Woosuk Kwon e6750d0b18 [V0 Deprecation] Remove unused classes in attention (#25541)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
2025-09-24 13:24:40 -07:00
Benjamin Chislettandlhsjohn c30b405b8f [Spec Decode] Enable FlashInfer Spec Decoding (#25196)
Signed-off-by: Benjamin Chislett <benjamin.chislett@centml.ai>
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Co-authored-by: lhsjohn <huashuoli@tencent.com>
2025-09-23 22:29:58 -04:00