11777 Commits

Author SHA1 Message Date
Ming Yang
0f67d4d962
[Attention] Add MLA prefill backend: trtllm_ragged_attention_deepseek (#26397)
Signed-off-by: Ming Yang <minos.future@gmail.com>
2025-10-24 10:24:08 -07:00
kourosh hakhamaneshi
7e1d697b56
[Bugfix] Fix MultiConnector stats reconstruction across process boundaries (#27366)
Signed-off-by: Kourosh Hakhamaneshi <Kourosh@anyscale.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
2025-10-24 17:08:05 +00:00
Chendi.Xue
699d62e6cf
[NIXL][BUGFIX] delay done_recving queue cleanup to bottom of get_finished (#27297)
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
2025-10-24 17:01:41 +00:00
Richard Zou
cd390b609d
[compile] Turn standalone_compile back on (#27460)
Signed-off-by: Richard Zou <zou3519@gmail.com>
2025-10-24 16:30:27 +00:00
Fadi Arafeh
2080b05099
[cpu][fix] Fix onednn_mm crash on consecutive matmuls with same M,K,N and different dtype (#27472)
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
2025-10-24 15:57:48 +00:00
Lifans
6454afec90
[Doc] Fix minor issues in docs/design/metrics.md (#27436)
Signed-off-by: Lifan Shen <lifans@meta.com>
2025-10-24 05:40:54 -07:00
Chauncey
41a62564a7
Fix test named tool use (#27458)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
2025-10-24 20:27:45 +08:00
fhl2000
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
ioana ghiban
435be10db9
Fix AArch64 CPU Docker pipeline (#27331)
Signed-off-by: Ioana Ghiban <ioana.ghiban@arm.com>
2025-10-24 05:11:01 -07:00
Cyrus Leung
b7030d962b
[Benchmark] Enable benchmark to run with encoding_format="bytes" (#27467)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-10-24 11:16:50 +00:00
Chauncey
3567816932
[Refactor] move tool parsing logic from protocol.py to the tool parser (#27383)
Co-authored-by: Aaron Pham <contact@aarnphm.xyz>
2025-10-24 09:53:23 +00:00
22quinn
e0ef8a2920
[BugFix] Fix torchrun DP with LLM class (#27395)
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
2025-10-24 08:11:37 +00:00
Isotr0py
42efe609ba
[MM][Bugfix] Replace PatchEmbed's conv3d to linear layer (#27418)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Roger Wang <hey@rogerw.io>
2025-10-24 07:32:47 +00:00
Yu Jiaqi
88d3141ec6
[Docs] remove v1 column for embedding models (#27446)
Signed-off-by: piood <2477084691@qq.com>
Signed-off-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2025-10-23 23:55:03 -07:00
Rui Qiao
09a6a49eaf
[Misc] Avoid "PyTorch non-writable tensors" warning in RayPPCommunicator (#27443)
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
2025-10-24 14:53:09 +08:00
strinczer
074475541a
[Bugfix] Fix Pydantic union resolution for ResponseFunctionToolCall in Responses API (#26706)
Signed-off-by: Shai Trinczer <strinczer@icloud.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
Co-authored-by: Ye (Charlotte) Qi <yeq@meta.com>
2025-10-23 22:53:42 -07:00
Aaron Pham
d4c574c39f
[Chore] remove structural tags logging lines (#27451) 2025-10-24 05:35:45 +00:00
usberkeley
c528b9006a
Fix EventPublisherFactory logic for disabled KV cache events (#27419)
Signed-off-by: Bradley <bradley.b.pitt@gmail.com>
2025-10-24 05:00:01 +00:00
fhl2000
85fee74b33
[Bugfix][CI] Move resolving cudagraph_mode before initializing attn_metadata_builder (#27427)
Signed-off-by: fhl2000 <63384265+fhl2000@users.noreply.github.com>
2025-10-23 20:31:14 -07:00
hfan
8dbe0c527f
[Misc] Add TPU usage report when using tpu_inference. (#27423)
Signed-off-by: Hongmin Fan <fanhongmin@google.com>
2025-10-23 20:29:37 -07:00
Xiangyu Li
5cc6bddb6e
[Kernel] Add GPTQv2 format support for low-bit or asymmetric quantization, by adapting gptq_gemm (#26092) 2025-10-23 23:26:13 -04:00
Harry Mellor
1f9460c4c1
Fix pooling adapters for Transformers backend (#27338)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-10-23 20:23:55 -07:00
xiao-llm
70022ffc00
Granite 4.0 quark quantization support (#26944)
Signed-off-by: Xiao YU <Xiao.YU@xilinx.com>
Signed-off-by: Xiao Yu <xiao.yu.dc@outlook.com>
Co-authored-by: Xiao YU <Xiao.YU@xilinx.com>
2025-10-24 02:14:03 +00:00
Akash kaothalkar
f417746ad7
[Hardware][POWERPC] Disable oneDNN path in vllm/model_executor/layers/utils.py for Powerpc (#27422)
Signed-off-by: Akash Kaothalkar <akash.kaothalkar@ibm.com>
Co-authored-by: Akash Kaothalkar <akash.kaothalkar@ibm.com>
2025-10-23 21:21:36 +00:00
Yu Jiaqi
0552cfb195
[Model] Siglip Embedding Support (#27324)
Signed-off-by: piood <2477084691@qq.com>
2025-10-23 20:19:48 +00:00
Kebe
51dd14ac2b
[Bugfix][DP] Fix creating too many DP Placement Groups (#26880)
Signed-off-by: Kebe <mail@kebe7jun.com>
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
Co-authored-by: Rui Qiao <ruisearch42@gmail.com>
2025-10-23 20:16:51 +00:00
Matthew Bonanni
dbfbf9f324
[Attention] Fix FlashMLA metadata builder arguments for q_len > 1 (#27368)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
2025-10-23 15:58:15 -04:00
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
Varun Sundar Rabindranath
a9f55dc588
[Misc] Add triton_kernels dependency (#27370)
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
2025-10-23 12:04:14 -07:00
Isotr0py
81d5bb765a
[Bugfix] Fix AWQ marlin layer skipping (#27416)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-10-23 18:30:28 +00:00
Gregory Shtrasberg
0825197bee
[Bugfix][ROCm][DeepSeek] Fix for forward_hip in rope for DeepSeek (#27373)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
2025-10-23 17:43:53 +00:00
Alexander Matveev
9ef3d5b875
[Bugfix] Fix dp_chunking enablement logic in FusedMoE layer (#27220)
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
2025-10-24 00:03:14 +08:00
Alexei-V-Ivanov-AMD
295c7f0267
Mirroring the test definitions (2025-10-22) (#27362)
Signed-off-by: Alexei V. Ivanov <alexei.ivanov@amd.com>
2025-10-24 00:02:26 +08:00
wang.yuqi
3fa2c12185
[Frontend][4/N] Improve all pooling task | Add plugin pooling task (#26973)
Signed-off-by: wang.yuqi <noooop@126.com>
Signed-off-by: Christian Pinto <christian.pinto@ibm.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Christian Pinto <christian.pinto@ibm.com>
2025-10-23 14:46:18 +00:00
Cyrus Leung
fe2016de2d
[CI/Build] Remove unnecessary flags from test registry (#27353)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-10-23 14:42:40 +00:00
Ilya Markov
237cf6d32a
[Misc] Remove use of CUDA_VISIBLE_DEVICES for device selection (fix DP slow startup time &c) (#26709)
Signed-off-by: ilmarkov <markovilya197@gmail.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
2025-10-23 20:58:39 +08:00
Navya Srivastava
faee3ccdc2
[Feature] Pydantic validation for speculative.py (#27156)
Signed-off-by: Navya Srivastava <navya.srivastava1707@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-10-23 12:19:33 +00:00
Bradley D
570c3e1cd4
[Bugfix] Honor --mm_encoder_attn_backend when used (#27124)
Co-authored-by: Bradley D <4551889+bradleyhd@users.noreply.github.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
2025-10-23 20:09:52 +08:00
Harry Mellor
3a4255c7c4
Run mypy on the lowest supported Python version instead of system Python (#27048)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-10-23 05:07:44 -07:00
tomeras91
61089465a6
[Model] Add MoE support for NemotronH (#25863)
Signed-off-by: Tomer Asida <57313761+tomeras91@users.noreply.github.com>
2025-10-23 10:27:23 +00:00
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
Chauncey
d00ce29d89
[CI] Reorganize entrypoints tests (#27403)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
2025-10-23 10:10:06 +00:00
Louie Tsai
3b7bdf983b
add SLA information into comparison graph for vLLM Benchmark Suite (#25525)
Signed-off-by: Tsai, Louie <louie.tsai@intel.com>
Signed-off-by: louie-tsai <louie.tsai@intel.com>
Signed-off-by: Louie Tsai <louie.tsai@intel.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-10-23 08:04:59 +00:00
Zhewen Li
50b788a17a
[CI/Build] Fix AMD CI: test_cpu_gpu.py (#27388)
Signed-off-by: zhewenli <zhewenli@meta.com>
2025-10-23 07:55:00 +00:00
Lucia Fang
fc059c7061
[Bugfix] Fix args settings for guided decoding args (#27375)
Signed-off-by: Lucia Fang <fanglu@fb.com>
2025-10-23 07:34:06 +00:00
Cyrus Leung
bfb240cc49
[CI/Build] Fix Prithvi plugin test (#27393)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-10-23 07:30:44 +00:00
Jonathan Chen
e255d92990
[Chore] Remove duplicate has_ functions in vllm.utils (#27372)
Signed-off-by: Jonathan <chenleejonathan@gmail.com>
2025-10-23 06:11:59 +00:00
wang.yuqi
3729ed00ba
[Model] Add num_cached_tokens for PoolingRequestOutput (#27378)
Signed-off-by: wang.yuqi <noooop@126.com>
2025-10-23 14:03:42 +08:00
Giancarlo Delfin
6644796bf4
[V1][spec decode] return logprobs for spec decoding (#26060)
Signed-off-by: Giancarlo Delfin <gdelfin@meta.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
2025-10-22 22:59:59 -07:00
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