 Bugen Zhao
|
285cbce6bd
|
[Rust Frontend] Resolve unified and split parser selections consistently (#56018)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-09-09 18:19:30 -07:00 |
|
|
Yan Ma
|
978c22f54b
|
[XPU] update triton-xpu 3.8.0 shim layer (#56014)
Signed-off-by: Yan Ma <yan.ma@intel.com>
|
2026-09-10 08:44:11 +08:00 |
|
|
Mikhail PodvitskiiandFlora Feng
|
65f3fca568
|
[Bugfix][Parser] Seed-OSS turn-boundary tokens + boundary-fallback tests (#54264)
Signed-off-by: Mikhail Podvitskii <podvitskiymichael@gmail.com>
Co-authored-by: Flora Feng <4florafeng@gmail.com>
|
2026-09-09 23:29:30 +00:00 |
|
|
Taneem Ibrahim
|
4ebf61ebda
|
[Cohere] Bound remaining request priorities to the MessagePack int64 range (#56146)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
|
2026-09-09 18:57:01 -04:00 |
|
|
ykamiset
|
83252ea899
|
[Performance][ROCm] Integrate aiter indexer scoring and top-k kernels into MiniMax-M3 sparse attention path (#52664)
Signed-off-by: Yamini Preethi Kamisetty <YaminiPreethi.Kamisetty@amd.com>
|
2026-09-09 15:40:33 -07:00 |
|
|
Aarushi Jain
|
6983a0883d
|
[ROCm][CI] Split MI300 Distributed Compile by graph partition mode (#53602)
Signed-off-by: Aarushi Jain <142941703+aarushjain29@users.noreply.github.com>
Signed-off-by: Aarushi Jain <aarushi.jain2@amd.com>
|
2026-09-09 17:07:51 -05:00 |
|
|
Andreas Karatzas
|
dcd544486b
|
[ROCm][Bugfix] Support shared KV prefill in AITER attention (#55887)
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
|
2026-09-09 14:51:34 -07:00 |
|
|
yzong-rh
|
26fec6d183
|
[Bugfix] Fix Step-3.5 reasoning parser for structured outputs (#53174)
Signed-off-by: Yifan Zong <yzong@redhat.com>
|
2026-09-09 17:10:23 -04:00 |
|
|
Wei ZhaoandOpenAI Codex
|
8c87c333b8
|
[Perf] Fix TRTLLM ragged prefill perf regression (#55499)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-09-09 20:38:20 +00:00 |
|
|
|
56d001faf0
|
[Bugfix] Detect OpenAI content format when message.content is passed through macro parameters (#53824)
Signed-off-by: wuhangxian <1391938827@qq.com>
Signed-off-by: wuhangxian <wuhangxian@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: wuhangxian <wuhangxian@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-09 20:10:28 +00:00 |
|
|
djramic
|
cce50657b7
|
[ROCm][CI] Use a platform-independent GEMM in the merged-column fuser test (#56130)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
|
2026-09-09 15:08:39 -05:00 |
|
|
Chris EastwoodandNick Hill
|
e8064a96d0
|
[Bugfix][V2] record_stream idx_mapping in the PP draft broadcast (#55745)
Signed-off-by: Chris Eastwood <chris.eastwood@pwn4g3.dev>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-09-09 12:55:56 -07:00 |
|
|
Aarushi Jain
|
c69d5d72a6
|
[CI][ROCm] Increase timeout for AMD MI355 Language Models (Standard) (#56114)
Signed-off-by: Aarushi Jain <aarushi.jain2@amd.com>
|
2026-09-09 18:10:26 +00:00 |
|
|
Divakar VermaandAndreas Karatzas
|
3fb676bfad
|
[ROCm][CI] Fix moe layer tests for fp8 dtype compatibility (#56106)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-09-09 17:48:14 +00:00 |
|
|
Guancheng Fu
|
a207d7ce1d
|
[Bugfix][LoRA] Log when an adapter applies no weights (#55310)
Signed-off-by: Guancheng Fu <110874468+gc-fu@users.noreply.github.com>
|
2026-09-09 17:44:46 +00:00 |
|
|
|
22d95d1adc
|
[Bugfix] Make mm_device_do_normalize encoder-cudagraph safe (#55370)
Signed-off-by: cjackal <44624812+cjackal@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
|
2026-09-10 01:43:22 +08:00 |
|
|
|
83fe99399e
|
[Spec Decode] Add NVFP4 DSpark gathered top-k projection (#55713)
Signed-off-by: Andrii Skliar <askliar@nvidia.com>
Co-authored-by: Andrii Skliar <askliar@nvidia.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-09 17:33:46 +00:00 |
|
|
Taneem Ibrahim
|
af51d0ef03
|
[Pooling] Report LoRA adapter names in responses (#56004)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
|
2026-09-09 13:31:13 -04:00 |
|
|
Aarushi JainandAarushi Jain
|
1454b71727
|
Fix ROCm AITER FP8 KV test tolerances. (#53590)
Signed-off-by: Aarushi Jain <aarushjain29@users.noreply.github.com>
Co-authored-by: Aarushi Jain <aarushjain29@users.noreply.github.com>
|
2026-09-09 12:22:25 -05:00 |
|
|
Harry MellorandClaude Opus 5
|
42d76ee35a
|
[Docs] Fix griffe docstring indentation warning in SupportsMRoPE (#56112)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-09-09 10:11:40 -07:00 |
|
|
Harry MellorandClaude Opus 5
|
719284fe15
|
[Core][Model] Unify XD-RoPE into M-RoPE and derive the channel count (#56078)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-09-09 09:23:30 -07:00 |
|
|
|
c55e15a44e
|
[Structured Output] Keep invalid structured-output requests from stopping the engine (#51450)
Co-authored-by: Lucas Bourtoule <35483370+dhalf@users.noreply.github.com>
Co-authored-by: Vadim Gimpelson <156319763+vadiklyutiy@users.noreply.github.com>
|
2026-09-09 15:32:01 +00:00 |
|
|
Andreas Karatzas
|
7e95735eb9
|
[Bugfix] Avoid FlexAttention recompiles when request counts change (#55888)
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
|
2026-09-09 08:10:25 -07:00 |
|
|
|
d8d53f17c2
|
[Rocm][Kimi-k3] Add pipeline_parallel support for the kimik3 model (#53664)
Signed-off-by: haic0 <149741444+haic0@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Shanshan Shen <467638484@qq.com>
|
2026-09-09 07:50:24 -07:00 |
|
|
Micah WilliamsonandFangzhou Ai
|
4e990dfcec
|
[ROCm] Bump AITER to v0.1.21.post2 (#55968)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
Co-authored-by: Fangzhou Ai <31551580+Fangzhou-Ai@users.noreply.github.com>
|
2026-09-09 07:49:59 -07:00 |
|
|
Ronen Schaffer
|
138d137b5b
|
[Refactor][kv_offload]: rename block→chunk (#52615)
Signed-off-by: Ronen Schaffer <ronen.schaffer@ibm.com>
|
2026-09-09 17:45:49 +03:00 |
|
|
|
9ffb8cea96
|
[CI] Add e2e test for scale-out EC connector flow (#54973)
Signed-off-by: zhouyou9505 <zhouyou9505@gmail.com>
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
Co-authored-by: zhouyou9505 <zhouyou9505@gmail.com>
Co-authored-by: Cursor Grok 4.6 <noreply@cursor.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-09-09 07:38:32 -07:00 |
|
|
|
cc4210f671
|
[Perf] Improve BF16x3 router GEMM accuracy and make it default on sm100 (#55899)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-09-09 07:33:12 -07:00 |
|
|
Harry Huangandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
3116c5d06b
|
[Qwen4Exp] Support UVA PLE-offload and Engram tensor parallelism (#54371)
Signed-off-by: huanghaoyan.hhy <huanghaoyan.hhy@alibaba-inc.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-09 07:32:34 -07:00 |
|
|
jimmy-adams
|
62f3bf58a5
|
[Bugfix][ROCm][DSv4] Skip launch_pdl=True JIT warmup when PDL is unsupported (#56035)
Signed-off-by: jimmy-adams <41593649+jimmy-adams@users.noreply.github.com>
|
2026-09-09 13:50:41 +00:00 |
|
|
Thomas OrtnerandHarry Mellor
|
e509d32b5a
|
[Transformers backend] Enable QKV-Fuser for Gemma4 (#55690)
Signed-off-by: Thomas Ortner <boh@zurich.ibm.com>
Signed-off-by: Thomas Ortner <bohnstinglthomas@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-09-09 14:46:31 +01:00 |
|
|
abrahamzewoudie
|
08b3e67b66
|
[ROCm][Perf] Fix Qwen3-vLLM audio encoder TP when heads are not divisible by TP size (#45900)
Signed-off-by: abrahamzewoudie <azewoudi@amd.com>
|
2026-09-09 13:28:24 +00:00 |
|
|
Adababyandshaolila
|
94848eda60
|
[Bugfix] Fix unreachable None guard in Molmo2 get_candidate_target_fps (#55893)
Signed-off-by: shaolila <shaolila@buaa.edu.cn>
Co-authored-by: shaolila <shaolila@buaa.edu.cn>
|
2026-09-09 12:37:10 +00:00 |
|
|
|
c7e9816c6a
|
[Bugfix][Rust Frontend] Skip undefined token ids in decode and anchor them zero-width (#55240)
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Codex <noreply@openai.com>
Signed-off-by: Feathbow <feathbow@gmail.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-09-09 09:55:04 +00:00 |
|
|
wliao2
|
474839f846
|
[CI/Build] Upload CPU nightly image to Docker Hub (#55163)
Signed-off-by: Liao, Wei <wei.liao@intel.com>
|
2026-09-09 17:13:48 +08:00 |
|
|
|
de650b55af
|
[Docs] Update README.md MkDocs to give option to run dev-server on different port. (#54584)
Signed-off-by: jcayab <42927334+jcayab@users.noreply.github.com>
Signed-off-by: Jefrey Cayab <jcayab@gmail.com>
Signed-off-by: Jefrey Cayab <42927334+jcayab@users.noreply.github.com>
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-09-09 09:08:12 +00:00 |
|
|
|
68dcc4fd86
|
[Rust Frontend] Make --max-model-len optional for the render server (#55328)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Signed-off-by: Wen Zhou <wenzhou@redhat.com>
|
2026-09-09 08:54:54 +00:00 |
|
|
|
5acd95906b
|
[Bugfix] Exclude DP token padding from draft attention metadata (#55458)
Signed-off-by: khluu <khluu000@gmail.com>
Signed-off-by: Kevin H. Luu <khluu000@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-09 01:47:45 -07:00 |
|
|
Nikhil KulkarniandClaude Fable 5.1
|
114abd1c11
|
[Bugfix][Frontend] Reject unsupported Responses API input items with 400 instead of 500 (#55974)
Signed-off-by: Nikhil Kulkarni <nikhilkulkarni1755@gmail.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
|
2026-09-09 07:51:45 +00:00 |
|
|
Yicong WangandOpenAI Codex
|
d2906091bf
|
[Bugfix] Fix Mooncake heterogeneous TP with replicated GQA heads (#52516)
Signed-off-by: wangyicong <wangyicong@bytedance.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-09-09 14:18:32 +08:00 |
|
|
Jing Wang
|
95cf420ac1
|
[CI][Test][Spec Decode] Fix CI failure of Qwen3 Omni DSpark loader mock (#56011)
Signed-off-by: Jing Wang <jingwang96@qq.com>
|
2026-09-08 23:06:15 -07:00 |
|
|
|
385dce36bc
|
[CI/Build][Hardware][NVIDIA] Add public CUDA 13.4 Rubin build path (#54640)
Signed-off-by: Meenakshi Venkataraman <meenakshiv@nvidia.com>
Signed-off-by: meena-at-work <80416898+meena-at-work@users.noreply.github.com>
Signed-off-by: Shang Wang <shangw@nvidia.com>
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Shang Wang <shangw@nvidia.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
|
2026-09-09 04:53:12 +00:00 |
|
|
|
bf7eee9d7b
|
[Bugfix][EC Connector] Fix ECExampleConnector load device under TP>1 (#40416)
Signed-off-by: Hang Gong <kidogong@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-09-09 11:44:30 +08:00 |
|
|
Bugen ZhaoandCodex
|
fc6b6e1feb
|
[Rust Frontend] Correctly parse whitespace framing in model output (#55417)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-09-09 13:40:13 +10:00 |
|
|
Qiming Zhang
|
27b63fb8f8
|
[CI][XPU] skip test_sampling_mask_tensors_match_finite_support on XPU (#55852)
Signed-off-by: mayuyuace <qiming1.zhang@intel.com>
|
2026-09-09 11:16:03 +08:00 |
|
|
Akine-Ko
|
41541636fd
|
[Refactor][EC Connector] Add backend extension points to ECCPUWorker (#54033)
Signed-off-by: Akine-Ko <2923601304@qq.com>
|
2026-09-08 20:13:47 -07:00 |
|
|
Tianyu GuoandOpenAI Codex
|
f1aeff6007
|
[Bugfix][EC Connector] Fail the request, not the engine, when a remote encoding cannot arrive (#55290)
Signed-off-by: Tianyu Guo <guoty@inferact.ai>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-09-08 20:13:33 -07:00 |
|
|
Bugen ZhaoandCodex
|
050f29caf1
|
[Rust Frontend] Simplify reasoning parser initialization and test organization (#55411)
Co-authored-by: Codex <noreply@openai.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-09-09 10:57:15 +08:00 |
|
|
djramicandAndreas Karatzas
|
c6ba5e89d6
|
[Bugfix][Elastic EP] Route only to surviving engines during scale-down (#55772)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-09-08 21:28:28 -05:00 |
|
|
djramic
|
21a117ad87
|
[CI][IR] Speed up vLLM IR test group (#55965)
Signed-off-by: Djordje Ramic <djoramic@amd.com>
|
2026-09-08 21:28:06 -05:00 |
|