Yuanheng Zhao and Harry Mellor
8d8855fdae
[Bugfix] Add safety check and fallback for null scaling factor ( #36106 )
...
Signed-off-by: Yuanheng Zhao <jonathan.zhaoyh@gmail.com >
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
2026-03-16 14:27:29 +00:00
Benjamin Bartels and Benjamin Bartels
0e5a9382af
[Bugfix] accept redacted thinking blocks in Anthropic messages ( #36992 )
...
Signed-off-by: Benjamin Bartels <benjaminba@tiglab-ubuntu.ilab.local >
Signed-off-by: bbartels <benjamin@bartels.dev >
Co-authored-by: Benjamin Bartels <benjaminba@tiglab-ubuntu.ilab.local >
2026-03-16 22:01:57 +08:00
Fynn Schmitt-Ulms
04bf5a35fa
[Spec Decode] Update extract_hidden_states to use deferred kv_connector clear ( #37013 )
2026-03-16 14:53:45 +01:00
Tianyu Guo
43a73f853b
Remove unused EVS functions in qwen3_vl.py ( #37183 )
...
Signed-off-by: Tianyu Guo <guoty9@mail2.sysu.edu.cn >
2026-03-16 13:09:09 +00:00
Julien Denize
ffbc2e5bdb
Patch Mistral config ( #37104 )
...
Signed-off-by: juliendenize <julien.denize@mistral.ai >
2026-03-16 12:22:18 +00:00
Lukas Geiger and Isotr0py
f9e6db3034
[Models][Qwen3 ViT] Keep max_seqlen on CPU to prevent D2H sync ( #37139 )
...
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com >
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn >
2026-03-16 12:11:59 +00:00
Artem Perevedentsev
f5e59ee7a6
[Performance] Add prefetch for checkpoints to OS page cache ( #36012 )
...
Signed-off-by: Artem Perevedentsev <aperevedents@nvidia.com >
2026-03-16 11:32:02 +00:00
Robin Nabel and Chauncey
bf9a185395
GLM4 tool parser: fix streaming mode ( #35208 )
...
Signed-off-by: Robin Nabel <opensource@nabel.co >
Co-authored-by: Chauncey <chaunceyjiang@gmail.com >
2026-03-16 18:48:52 +08:00
Harry Mellor
ad041c79db
Fix text only inputs for MRoPE models with the Transformers modelling backend ( #37055 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
2026-03-16 10:31:16 +00:00
Kunshang Ji
747b068136
[Hardware] Replace memory related torch.cuda APIs ( #37031 )
...
Signed-off-by: Kunshang Ji <jikunshang95@gmail.com >
2026-03-16 10:24:48 +00:00
Harry Mellor
122f75d939
Fix pipeline parallel with multimodal models with the Transformers modelling backend ( #37057 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
2026-03-16 10:20:37 +00:00
Roy Wang
0115e957d4
[Frontend][Misc] Remove unused log in /is_sleeping ( #37093 )
...
Signed-off-by: esmeetu <jasonailu87@gmail.com >
2026-03-16 17:46:28 +08:00
haosdent
116ed130f4
[Bugfix] Fix GDN attention crash with mixed decode/spec-decode batches ( #34871 )
...
Signed-off-by: haosdent <haosdent@gmail.com >
2026-03-16 10:30:23 +01:00
Vadim Gimpelson
8374387bd8
[FlashInfer] Revert block_size 16 + head_size 256 workaround on Blackwell ( #36987 )
...
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com >
2026-03-16 09:04:29 +00:00
Isotr0py
912fbe9555
[Bugfix] Fix Qwen2.5-Omni/Qwen3-Omni use_audio_in_video with multi-video inputs ( #37147 )
...
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn >
2026-03-16 08:56:06 +00:00
Laith Sakka
52131f88d9
use skip_all_guards_unsafe to drop global_state and torch_function_mode_stack guards instead of previous hacks ( #36204 )
...
Signed-off-by: Laith Sakka <lsakka@meta.com >
2026-03-16 08:52:31 +00:00
Roy Wang
821eb80c0d
[Performance][Model Loader] Skip non-local expert weights during EP model loading ( #37136 )
...
Signed-off-by: esmeetu <jasonailu87@gmail.com >
2026-03-16 01:33:36 -07:00
Andreas Karatzas
911355e216
[ROCm] Fix KV copy methods and auto-select attention backend for ROCm ( #36845 )
...
Signed-off-by: Andreas Karatzas <akaratza@amd.com >
2026-03-16 16:07:27 +08:00
Chauncey
8d3f8f485e
[Bugfix] fix Qwen3.5 tool calling bug ( #36774 )
...
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com >
2026-03-16 15:38:42 +08:00
Woosuk Kwon
96efb91480
[Model Runner V2] Fix processed logits in sample() ( #37144 )
...
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai >
2026-03-16 00:35:49 -07:00
2754231ba3
[Kernel] Add FlashInfer MoE A2A Kernel ( #36022 )
...
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com >
Signed-off-by: Leo Tian <lctian@nvidia.com >
Co-authored-by: wzhao18 <wzhao18.sz@gmail.com >
Co-authored-by: Stefano Castagnetta <scastagnetta@nvidia.com >
Co-authored-by: root <root@lyris0267.lyris.clusters.nvidia.com >
2026-03-15 23:45:32 -07:00
bigshanedogg
2390d44209
[Model] Add HyperCLOVAX-SEED-Think-14B language model support ( #37107 )
...
Signed-off-by: bigshanedogg <bigshane319@gmail.com >
2026-03-16 06:40:05 +00:00
Li, Jiang
7362b4450a
[Bugfix] Avoid LD_PRELOAD check on MacOS ( #37145 )
...
Signed-off-by: jiang1.li <jiang1.li@intel.com >
2026-03-15 23:31:44 -07:00
Andreas Karatzas
57a314d155
[CI][Bugfix] Fix 500 errors from priority overflow and TemplateError subclasses in schema fuzz tests ( #37127 )
...
Signed-off-by: Andreas Karatzas <akaratza@amd.com >
2026-03-16 05:27:21 +00:00
Wang, Yiting
68e1b711f1
[XPU] Add deepseek_scaling_rope fused kernel ( #36612 )
...
Signed-off-by: yitingw1 <yiting.wang@intel.com >
2026-03-16 12:35:08 +08:00
rasmith
0024f39a32
[ROCm][P/D][MORI][BugFix] Add transfer_id for moriio_connector so moriio_connector to restore P/D functionality ( #34907 )
...
Signed-off-by: Randall Smith <Randall.Smith@amd.com >
2026-03-16 10:36:51 +08:00
7acaea634c
In-Tree AMD Zen CPU Backend via zentorch [1/N] ( #35970 )
...
Signed-off-by: Lalithnarayan C <Lalithnarayan.C@amd.com >
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com >
Co-authored-by: Chinmay-Kulkarni-AMD <Chinmay.Kulkarni@amd.com >
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com >
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com >
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-03-15 23:35:35 +00:00
Jiangyun Zhu and Roger Wang
697e4ff352
[GDN] add a config for gdn kernel selection ( #36647 )
...
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com >
Co-authored-by: Roger Wang <hey@rogerw.io >
2026-03-16 00:40:17 +08:00
Hari
a3e2e250f0
[Feature] Add Azure Blob Storage support for RunAI Model Streamer ( #34614 )
...
Signed-off-by: hasethuraman <hsethuraman@microsoft.com >
2026-03-15 19:38:21 +08:00
Isotr0py
143e4dccdf
[Misc] Add online audio_in_video test ( #36775 )
...
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn >
2026-03-15 00:14:11 -07:00
Isotr0py
6590a3ecda
[Frontend] Remove torchcodec from audio dependency ( #37061 )
...
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn >
2026-03-15 05:15:59 +00:00
Nick Hill
458c1a4b2d
[Frontend] Reduce chat template warmup logging levels ( #37062 )
...
Signed-off-by: Nick Hill <nickhill123@gmail.com >
2026-03-14 13:48:59 -07:00
Karan Bansal and Inokinoki
821fde2df4
[Bugfix] Fix xgrammar dtype mismatch on macOS CPU inference ( #32384 )
...
Signed-off-by: Karan Bansal <karanb192@gmail.com >
Co-authored-by: Inokinoki <inoki@inoki.cc >
2026-03-14 17:29:06 +00:00
arlo
8c29042bb9
[Feature] Add InstantTensor weight loader ( #36139 )
2026-03-14 18:05:23 +01:00
Cyrus Leung
5467d137b3
[Frontend] Avoid startup error log for models without chat template ( #37040 )
...
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk >
2026-03-14 09:36:11 -07:00
Santino Ramos
3ed46f374b
[Model Runner V2] Add Support for XD-RoPE ( #36817 )
...
Signed-off-by: Santino Ramos <elsantinoramos@gmail.com >
2026-03-14 09:27:55 -07:00
seanmamasde
84868e4793
[Bugfix][Frontend] Fix audio transcription for MP4, M4A, and WebM formats ( #35109 )
...
Signed-off-by: seanmamasde <seanmamasde@gmail.com >
2026-03-14 08:44:03 -07:00
Isotr0py
a8e8d62dd8
[Misc] Clean up Kimi-audio whisper encoder loading ( #36903 )
...
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn >
2026-03-14 23:37:52 +08:00
e42b49bd69
Mistral common v10 ( #36971 )
...
Signed-off-by: juliendenize <julien.denize@mistral.ai >
Signed-off-by: Julien Denize <40604584+juliendenize@users.noreply.github.com >
Co-authored-by: root <root@h200-bar-196-227.slurm-bar-compute.tenant-slurm.svc.cluster.local >
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk >
2026-03-14 07:26:43 -07:00
Sergey Zinchenko
4a718e770d
[Bug] Fix Failure in /v1/chat/completions/render for Multimodal Requests ( https://github.com/vllm-project/vllm/issues/35665 ) ( #35684 )
2026-03-14 14:10:11 +00:00
Harry Mellor
ffa5d74f15
Enable loading of fused expert weights in the Transformers modelling backend ( #36997 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
2026-03-14 07:01:06 +00:00
sbeurnier
a116f96930
[V1] Remove pin_memory() in async_copy_to_gpu to fix sporadic stalls ( #37006 )
...
Signed-off-by: Sebastien Beurnier <sbeurnier@together.ai >
2026-03-14 01:37:32 +00:00
Li, Jiang and gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
092ace9e3a
[UX] Improve UX of CPU backend ( #36968 )
...
Signed-off-by: jiang1.li <jiang1.li@intel.com >
Signed-off-by: Li, Jiang <bigpyj64@gmail.com >
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-03-14 09:27:29 +08:00
f680dc1b39
[responsesAPI] prioritize content over summary in reasoning item input ( #36516 )
...
Signed-off-by: Andrew Xia <axia@meta.com >
Signed-off-by: Andrew Xia <mitandrewxia@gmail.com >
Signed-off-by: Andrew Xia <axia@fb.com >
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Andrew Xia <axia@fb.com >
2026-03-14 09:20:30 +08:00
b41aa264f9
fix: resolve chat template names before kwargs detection ( #36937 )
...
Co-authored-by: giulio-leone <giulio.leone@users.noreply.github.com >
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com >
2026-03-14 00:20:16 +00:00
Dimitrios Bariamis and Dimitrios Bariamis
367cf5cd3e
[Feat][Bugfix] Enable additional dimension for Flashinfer MLA and fix routing dtype ( #36931 )
...
Signed-off-by: Dimitrios Bariamis <12195802+dbari@users.noreply.github.com >
Co-authored-by: Dimitrios Bariamis <12195802+dbari@users.noreply.github.com >
2026-03-13 16:41:16 -07:00
haosdent
6d53efd2a5
[Bugfix] Fix MLA attention crash with AWQ/GPTQ quantized models ( #34695 )
...
Signed-off-by: haosdent <haosdent@gmail.com >
2026-03-13 23:25:41 +00:00
Benjamin Chislett
8b346309a5
[Refactor] Consolidate SupportsEagle ( #36063 )
...
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com >
2026-03-13 23:22:40 +00:00
Nick Hill
54a6db827f
[BugFix] Fix "DP Coordinator receives unexpected..." messages ( #37008 )
...
Signed-off-by: Nick Hill <nickhill123@gmail.com >
2026-03-13 23:18:05 +00:00
Matthew Bonanni
9efc4db965
[Bugfix] Fix DeepSeek-V3.2 tokenizer stripping spaces ( #37004 )
...
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com >
2026-03-13 22:55:36 +00:00
