 Michael Lapshin
|
d421a2e8fc
|
[Perf] Remove CPU-GPU sync in heterogeneous vocabulary speculative decoding (#57396)
|
2026-09-22 18:34:19 -04:00 |
|
|
Thang NguyenandClaude Opus 5.5
|
4edb55169f
|
[CI] Shard (H200 MIG 18GB) Spec Decode Draft Model across whole-directory replicas (#58193)
Signed-off-by: Thang Nguyen <thangnguyenvn647@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
|
2026-09-22 14:50:18 -07:00 |
|
|
Thang NguyenandKimi
|
4ec0b95c44
|
[CI] Split LM Eval TurboQuant KV Cache into per-config jobs (#57113)
Signed-off-by: Thang Nguyen <thangnguyenvn647@gmail.com>
Co-authored-by: Kimi <noreply@moonshot.ai>
|
2026-09-22 14:49:06 -07:00 |
|
|
Misha Goin
|
5c3b61e9c4
|
[Core] Disable JIT warmup in eager mode (#58197)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-09-22 17:35:23 -04:00 |
|
|
Misha Goin
|
01e15bc94c
|
[Bugfix] Backport Inductor custom-op pattern matching fix (#58189)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-09-22 14:26:49 -07:00 |
|
|
Andrey Talman
|
ecdd11d0e0
|
[CI] Build the torch-nightly image on Ubuntu 24.04 (#58204)
|
2026-09-22 14:15:57 -07:00 |
|
|
Misha Goin
|
25965ee583
|
[Kernel] Remove AllSpark INT8 W8A16 GEMM backend (#58001)
Signed-off-by: mgoin <mgoin64@gmail.com>
|
2026-09-22 14:07:34 -07:00 |
|
|
|
1b3b88ec2b
|
[Core] structured generation mode for DiffusionGemma model (Jev-like) (#57250)
Signed-off-by: Matt Mastracci <matthew@mastracci.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Razorback16 <razorback16@protonmail.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Razorback16 <razorback16@protonmail.com>
|
2026-09-22 20:51:17 +00:00 |
|
|
Wentao Ye
|
fae5cbfc8b
|
[Refactor] Remove dead code multiple places (#58002)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-09-22 16:36:03 -04:00 |
|
|
lucamotz
|
276db94fb2
|
[Bugfix][Model][Spec Decode] Defer disposable GLM MTP head (#55442)
Signed-off-by: Luca Motz <luca.motz@icloud.com>
|
2026-09-22 20:08:27 +00:00 |
|
|
hclandmgoin
|
71a2392845
|
[Bugfix][V1] Read ModelState max_model_len from model config (#58149)
Signed-off-by: Chenglun Hu <chenglunhu@gmail.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
|
2026-09-22 19:45:04 +00:00 |
|
|
Divakar VermaandAndreas Karatzas
|
d1f63f2af9
|
[ROCm][CI] Add GELU activation for AiterExperts in the modular-kernel coverage (#58030)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-09-22 14:39:13 -05:00 |
|
|
pengyihangandmgoin
|
415e11c6f1
|
[Bugfix][V1] Honor enable_jit_warmup for V2 kernel warmup (#55146)
Co-authored-by: mgoin <mgoin64@gmail.com>
|
2026-09-22 15:34:31 -04:00 |
|
|
Taneem Ibrahim
|
bc162b3f92
|
[MRV2] Release weight offloader on shutdown (#57834)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
|
2026-09-22 15:01:20 -04:00 |
|
|
Guanxin LiandFlora Feng
|
f944491db9
|
[Bugfix] batch_invariant: keep non-AllReduce collectives enabled on NCCL >= 2.31 (#58179)
Signed-off-by: Guanxin Li <38149783+guanxingithub@users.noreply.github.com>
Co-authored-by: Flora Feng <4florafeng@gmail.com>
|
2026-09-22 14:44:00 -04:00 |
|
|
siyuandIsotr0py
|
c024cfdb02
|
[Fast Start] Support data parallelism in the weight cache daemon (#57386)
Signed-off-by: liusy58 <mg21330037@smail.nju.edu.cn>
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
|
2026-09-22 18:19:40 +00:00 |
|
|
|
ca831d1c55
|
[ROCm][DSv4.1][Perf] Fuse the inverse RoPE into the sparse decode reduce (#57435)
Signed-off-by: Fangzhou Ai <fangzhou.ai@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-22 18:05:11 +00:00 |
|
|
stefankoncarevicandAndreas Karatzas
|
72675c4706
|
[Bugfix][ROCm] Dispatch the QuantFP8 CUDA fallback on the class (#58136)
Signed-off-by: Stefan Koncarevic <Stefan.Koncarevic@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-09-22 17:49:11 +00:00 |
|
|
Gilles TurpinandWentao Ye
|
74370a0e30
|
[Bugfix] hadacore_transform: respect inplace parameter to fix garbage outputs with QuIP transforms (#43462)
Signed-off-by: Gilles Turpin <turpingilles15@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2026-09-22 12:48:20 -04:00 |
|
|
|
a6131b0e65
|
[Bugfix][Engram] Fall back when /dev/shm is absent before sharing tables (#57914)
Signed-off-by: Juntian Liu <juntianl@inferact.ai>
Signed-off-by: Juntian Liu <Juntianl777@gmail.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-23 00:19:09 +08:00 |
|
|
|
066ee91197
|
[Bugfix][Attention] Avoid NaN in the Triton softcap for large attention logits (#56579)
Signed-off-by: Kushal Dabbe <72650064+kushaldabbe@users.noreply.github.com>
Co-authored-by: opencode <noreply@opencode.ai>
Co-authored-by: Misha Goin <mgoin64@gmail.com>
|
2026-09-22 12:11:05 -04:00 |
|
|
Tony Lin
|
c42f5285ec
|
[Bugfix] prioritize architecture capability before DeepGEMM availability check (#58073)
Signed-off-by: Tony Lin <tony.lin@intel.com>
|
2026-09-22 11:38:04 -04:00 |
|
|
aoshen02
|
feb87b1934
|
[Bugfix] Narrow AuxOutput KV restrictions to known PD connectors (#58150)
Signed-off-by: aoshen02 <aoshen@inferact.ai>
|
2026-09-22 23:09:39 +08:00 |
|
|
Lucas WilkinsonandClaude Fable 5.1
|
5c121e962a
|
[SpecDecode] Restore residual-logits comments in _resample_kernel (#58166)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
|
2026-09-22 08:07:31 -07:00 |
|
|
Tony LinandFlora Feng
|
e4340e41c9
|
[Feat][XPU] VLLM_BATCH_INVARIANT support for Dense/MoE models (#55881)
Signed-off-by: Tony Lin <tony.lin@intel.com>
Co-authored-by: Flora Feng <4florafeng@gmail.com>
|
2026-09-22 11:06:54 -04:00 |
|
|
Artem PerevedentsevandCNE Pierre FICHEPOIL
|
1ea7c63f4a
|
[Bugfix][Structured Output] Disallow MRV1 + PP>1 + async sched + structured output (#56250)
Signed-off-by: Artem Perevedentsev <aperevedents@nvidia.com>
Co-authored-by: CNE Pierre FICHEPOIL <pierre-1.fichepoil@gendarmerie.interieur.gouv.fr>
|
2026-09-22 18:00:05 +04:00 |
|
|
|
c9b34fdb2d
|
[Bugfix][GLM-5.3-Flash] Run the dense MLP layers on the sequence-parallel shard (#58061)
Signed-off-by: Jared Wen <w13431838023@gmail.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-22 21:58:21 +08:00 |
|
|
Jee Jee Li
|
d90f0eade5
|
[Build] Fix CUDA 12 KV connector dependency selection (#57945)
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
|
2026-09-22 06:13:07 -07:00 |
|
|
|
e548298f81
|
[Bugfix][Structured Outputs] Reject empty structural_tag at request validation (#47450)
Signed-off-by: linnea-lin-00638949 <15521435947@163.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Artem Perevedentsev <aperevedents@nvidia.com>
|
2026-09-22 16:09:39 +03:00 |
|
|
xiangdongandKunshang Ji
|
362a64b21d
|
[XPU][CI]Remove model_runner_v2 test from Intel GPU CI (#58050)
Signed-off-by: zengxian <xiangdong.zeng@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-09-22 19:56:01 +08:00 |
|
|
|
9815732c16
|
[BugFix][Core] Make the structured-output grammar poll non-blocking (#55931)
Signed-off-by: ubwzwd <ubwzwd@gmail.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: Artem Perevedentsev <aperevedents@nvidia.com>
|
2026-09-22 14:39:47 +03:00 |
|
|
Bugen ZhaoandCodex
|
81d7293c21
|
[Rust Frontend] Construct model-owned vision processors through specs (#58109)
Co-authored-by: Codex <noreply@openai.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-09-22 10:01:53 +00:00 |
|
|
Louie TsaiandHarry Mellor
|
6dc34b6334
|
[CPU] Add device-memory-utilization CLI alias (#56547)
Signed-off-by: louie-tsai <louie.tsai@intel.com>
Signed-off-by: Louie Tsai <louie.tsai@intel.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-09-22 17:37:15 +08:00 |
|
|
|
91d7324cb1
|
[perf] wire FA and FlashMLA for sm90 GLM5Next NoPE SparseMLA (#55385)
Signed-off-by: JaredforReal <w13431838023@gmail.com>
Co-authored-by: Kimi Code <noreply@moonshot.cn>
Co-authored-by: Leoyzen <leoyzen@gmail.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
|
2026-09-22 02:03:59 -07:00 |
|
|
Kevin H. LuuandClaude Fable 5.1
|
64a48b19b4
|
[CI] Emit a kernel symbol map from the csrc build (opt-in, for test selection) (#58097)
Signed-off-by: khluu <khluu000@gmail.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
|
2026-09-22 01:37:34 -07:00 |
|
|
|
f92b78f6ef
|
[Kernel][DSV4.1] Fuse MXFP8 wo_b GEMM with sequence-parallel reduce-scatter (#57428)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
Signed-off-by: Canlin <canlinguosdu@gmail.com>
Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-09-22 01:07:17 -07:00 |
|
|
Bugen Zhao
|
a6c47fbbf4
|
[Rust Frontend] Separate multimodal instrumentation from request timing (#58084)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-09-22 06:57:56 +00:00 |
|
|
yinfengLiuandShanshan Shen
|
2af05512cf
|
[Kernel] Add opt-in load-time MXFP4 dequantization (#50814)
Signed-off-by: Liuyinfeng01 <yinfeliu@amd.com>
Co-authored-by: Shanshan Shen <467638484@qq.com>
|
2026-09-22 14:51:12 +08:00 |
|
|
Mikko TukiainenandCursor
|
68363d64ec
|
[ROCm][Perf] Avoid extra reshape kernel in Qwen GDN output norm (#47842)
Signed-off-by: Mikko Tukiainen <Mikko.Tukiainen@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-09-22 14:38:16 +08:00 |
|
|
Bugen ZhaoandCodex
|
496c6472cb
|
[Rust Frontend] Build full-output grammars from initialized reasoning parsers (#57340)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-09-22 06:11:55 +00:00 |
|
|
Ting SUNandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
a33b3bac5d
|
[Bugfix][Qwen2.5-VL] Honor video fps for temporal M-RoPE (#47736)
Signed-off-by: Ting Sun <suntcrick@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-22 05:56:12 +00:00 |
|
|
shaohuaxiandCodex
|
5abf85d27a
|
[Bugfix][Frontend] Validate mixed prompt embedding mask lengths (#57006)
Signed-off-by: 子华 <huaxi.shx@alibaba-inc.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-09-22 05:50:31 +00:00 |
|
|
Juan Pérez de Algaba
|
4800024b98
|
[Security] Reject min_tokens that exceeds the filled max_tokens default (#57731)
Signed-off-by: Juan Pérez de Algaba <jperezde@redhat.com>
|
2026-09-22 05:50:23 +00:00 |
|
|
Bugen ZhaoandClaude Fable 5.1
|
d50723df04
|
[Rust Frontend] Introduce parser-owned output grammar interfaces (#55269)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
|
2026-09-22 05:35:07 +00:00 |
|
|
|
f84325c48c
|
[Frontend][Rust] Add mm-processor benchmark for Rust frontend (#51922)
Signed-off-by: Karthik Gangula <gangula-karthik@users.noreply.github.com>
Signed-off-by: gangula-karthik <gkarthik923@gmail.com>
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: Karthik Gangula <gangula-karthik@users.noreply.github.com>
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
|
2026-09-22 05:08:35 +00:00 |
|
|
Jeff (Junze) Ma
|
0961bbae28
|
[Spec Decode] Enable async scheduling for DFlash (#58065)
|
2026-09-21 22:05:44 -07:00 |
|
|
Shanshan Shen
|
42a85a4976
|
[ROCm][Bugfix] Explicitly reject FSE=1 with DPA+ETP deployment for DeepSeek-V4 (#57919)
Signed-off-by: Shanshan Shen <87969357+shen-shanshan@users.noreply.github.com>
|
2026-09-22 04:45:53 +00:00 |
|
|
|
639461eda4
|
[RL][Sleep] Retain frozen weights across level-2 sleep (#57891)
Signed-off-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-09-22 12:36:55 +08:00 |
|
|
Yicong Wang
|
c4d424c2e2
|
[Bugfix][Spec Decode] Cap DFlash/DSpark profiling query batch (#56448)
Signed-off-by: wangyicong <wangyicong@bytedance.com>
|
2026-09-22 12:36:32 +08:00 |
|
|
Bugen ZhaoandCodex
|
ff3c9cba3f
|
[Rust Frontend] Add MiMo V2.5 parser support (#57933)
Co-authored-by: Codex <noreply@openai.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-09-22 04:27:09 +00:00 |
|