 TJian
|
1806d1adfc
|
[ROCm] [DSv4] [Perf] Support DeepSeek v4 MTP (#43385)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
|
2026-05-24 18:43:08 +08:00 |
|
|
Andreas Karatzas
|
5940590855
|
[ROCm][CI] Stabilize 400 error return code for invalid schema inputs (#43016)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2026-05-24 10:06:49 +00:00 |
|
|
Or Ozeri
|
357fddf614
|
[kv_offload]: Add DSv4 support (#43142)
Signed-off-by: Or Ozeri <oro@il.ibm.com>
|
2026-05-24 11:10:12 +03:00 |
|
|
Gabriel Wu
|
82536acc54
|
Keep scheduler alive for delayed KV connector frees (#43433)
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com>
|
2026-05-23 06:23:32 +00:00 |
|
|
Xiaogang Zhouandxiaogang.zhou
|
d19db10974
|
[Bugfix] Fix native Triton top-k/top-p kernel assumes contiguous logi… (#42739)
Signed-off-by: xiaogang.zhou <xiaogang.zhou@bytedance.com>
Co-authored-by: xiaogang.zhou <xiaogang.zhou@bytedance.com>
|
2026-05-22 22:56:16 -07:00 |
|
|
Taneem Ibrahim
|
3a1c062151
|
[Misc] Added missing return type annotations to improve mypy and IDE tooling (#43383)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
|
2026-05-23 13:28:22 +08:00 |
|
|
Andreas Karatzas
|
6a4723a2e0
|
[ROCm][CI] Stabilize runner teardown between sampler tests (#43023)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2026-05-23 12:19:54 +08:00 |
|
|
Sumanth R Hegdeandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
3cb83c9592
|
Add model to WeightTransferEngine.__init__ (#42922)
Signed-off-by: SumanthRH <sumanthrh99@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-05-22 17:52:15 -07:00 |
|
|
Duncan Moss
|
552bbe6f4e
|
[Attention] Add head_dim=512 support for FlashInfer trtllm attention backend (#38822)
|
2026-05-22 20:27:35 -04:00 |
|
|
Ma JianandKunshang Ji
|
8de5cabeb7
|
[XPU]fix: add XPU platform guards to DeepSeek-V4 ops (#42950)
Signed-off-by: Ma Jian <jian1.ma@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-05-23 06:29:45 +08:00 |
|
|
Benjamin Chislettandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
4e2eba28be
|
[Perf] Optimize hidden state extraction logic (#37374)
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Signed-off-by: Benjamin Chislett <chislett.ben@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
2026-05-22 18:23:08 -04:00 |
|
|
Nick Hill
|
47d4407d7c
|
[Model Runner V2] Support sharing kv cache layers (#35045)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-05-22 22:18:23 +00:00 |
|
|
Yongye Zhu
|
843715739b
|
[Refactor] Extract DeepSeek V4 sparse MLA impl into model folder (#43149)
|
2026-05-22 10:06:31 -07:00 |
|
|
Zhanda ZhuandShang Wang
|
c7624bea5e
|
[Bugfix] Source num_qo_heads from Attention layers in Flashinfer/Triton metadata builders (#42650)
Signed-off-by: zhanda <zhandazhu@gmail.com>
Co-authored-by: Shang Wang <shangw@nvidia.com>
|
2026-05-22 16:10:03 +00:00 |
|
|
Isotr0py
|
f0feb15e7f
|
[Multimodal] Simplify ViT CUDA graph interfaces (#41234)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
|
2026-05-22 22:31:00 +08:00 |
|
|
Tobias Wasner
|
4658bf882b
|
[Bugfix] Clear P0 mm sender cache on sleep/pause to fix mm_hash desync (#43001)
Signed-off-by: Tobias Wasner <wasnertobias@gmail.com>
|
2026-05-22 03:54:29 -07:00 |
|
|
|
b3c7ffcab8
|
[Misc] Replace assert with proper exceptions for security and validation in pooling (#43286)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-05-22 18:43:33 +08:00 |
|
|
Li, Jiang
|
65b7a812a2
|
[CPU] Experimentally enable Triton and MRV2 (#43225)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
|
2026-05-22 01:48:17 -07:00 |
|
|
haosdentandWentao Ye
|
5ea76fa89a
|
[CI] Fix test_lora_with_spec_decode on V2 model runner (#43314)
Signed-off-by: haosdent <haosdent@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2026-05-22 14:24:18 +08:00 |
|
|
Lanze Liu
|
39d5fa96a7
|
[Bugfix] Zero stale is_prefilling in padded CUDA graph rows for Mamba (#41873)
Signed-off-by: Lanze Liu <lanzetech@gmail.com>
|
2026-05-21 15:42:42 -07:00 |
|
|
Nick Hill
|
565b745ec5
|
[BugFix] Use correct logprobs for logprob_token_ids (#43125)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-05-21 15:42:20 -07:00 |
|
|
Wentao Ye
|
b29cbf0652
|
[Perf] zeros -> empty to remove additional fill (#42988)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-05-21 16:00:29 -04:00 |
|
|
Francesco Fuscoandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
b730c46352
|
[Perf] [Hybrid] Fused Triton kernel for GPU-side Mamba state postprocessing (#40172)
Signed-off-by: Francesco Fusco <ffu@zurich.ibm.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-05-21 04:50:54 -07:00 |
|
|
|
c68c55d43e
|
[CPU][RISC-V] Add VLEN=256 support to RVV attention kernels (#42943)
Signed-off-by: velonica0 <like@mail.nankai.edu.cn>
Signed-off-by: velonica0 <47554626+velonica0@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
|
2026-05-21 04:50:49 -07:00 |
|
|
Nick HillandBugen Zhao
|
f2ace1d57d
|
[Frontend][RFC] Rust front-end integration (#40848)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
|
2026-05-21 12:24:48 +08:00 |
|
|
Wentao YeandNick Hill
|
9640970de2
|
[Model Runner V2] Fix lora Triton Error [CUDA]: device-side assert triggered (#43139)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-05-21 01:00:30 +00:00 |
|
|
rishitdholakia13andCursor
|
ded871201a
|
[Bug][Structured Outputs] Fix bug that leads to unconstrained generations with structural tags (#42452)
Signed-off-by: rishitdholakia13 <rishit+github@cohere.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-05-20 07:08:58 -07:00 |
|
|
Kebe
|
19cf334207
|
[Feature] Support manually enabling the cumem allocator (#33648)
Signed-off-by: Kebe <mail@kebe7jun.com>
|
2026-05-20 08:58:30 -04:00 |
|
|
Ronen Schaffer
|
4f940896a3
|
[KV Offload] Pass OffloadingSpec instead of VllmConfig to secondary tiers (#43076)
Signed-off-by: Ronen Schaffer <ronen.schaffer@ibm.com>
|
2026-05-20 03:32:08 +00:00 |
|
|
Izik Golan
|
2ae910ed88
|
[Perf] Avoid forward scan for async output placeholders (#42938)
|
2026-05-19 20:16:07 -07:00 |
|
|
Benjamin Chislett
|
c628a93a64
|
[Perf][Bugfix] Update dflash aux layer indexing (#40727)
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
|
2026-05-19 20:15:57 -07:00 |
|
|
Nick Hill
|
39bba710be
|
[MRV2][BugFix] Fix default-stream CG capture in P/W LoRA case (#43160)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-05-19 19:19:05 -07:00 |
|
|
Doğaç Eldenk
|
1242196295
|
[Model] Support post-norm architecture for EAGLE-3 supeculators (#42764)
Signed-off-by: Doğaç Eldenk <dogacel@gmail.com>
|
2026-05-19 13:39:00 -07:00 |
|
|
Dom Brown
|
d247a931cc
|
[feat] Add FP8 per-tensor Q scale support to Triton attention backend (#42080)
Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
|
2026-05-19 09:02:05 -07:00 |
|
|
Xinyu Chen
|
d740e2c029
|
[XPU] update xpu graph usage (#43043)
Signed-off-by: Xinyu Chen <xinyu1.chen@intel.com>
|
2026-05-19 23:09:07 +08:00 |
|
|
Nick Hill
|
b82e908b4c
|
[Perf][4/n] Eliminate various GPU<->CPU syncs (#42347)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-05-19 10:35:54 -04:00 |
|
|
Aaron Haoandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
f34623bf3c
|
[bug] AsyncScheduler drops first post-resume token after pause_generation + clear_cache (#42117)
Signed-off-by: hao-aaron <ahao@anyscale.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-05-19 01:06:21 -07:00 |
|
|
Woosuk Kwon
|
b14be81c1f
|
[Model Refactoring] Move deepseek_v4_ops to models/deepseek_v4 [3/N] (#43073)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
|
2026-05-19 00:52:54 -07:00 |
|
|
|
fab07e4d0f
|
[Bugfix][KV Connector] Fix SimpleCPUOffloadScheduler TOCTOU between Phase A and Phase B (#42289)
Signed-off-by: Qiuyang Yue <yueqiuyang1389@gmail.com>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: gemini-code-assist <noreply@google.com>
|
2026-05-18 21:22:33 -07:00 |
|
|
gnovackandgeorge
|
3ca8db2ef8
|
add cutedsl dsv4 indexer fp8 kernel (#42899)
Signed-off-by: george <george@inferact.ai>
Co-authored-by: george <george@inferact.ai>
|
2026-05-18 21:17:56 -07:00 |
|
|
Woosuk Kwon
|
87b08c5f64
|
[Model Refactoring] Move DeepSeek V4 layers to models/deepseek_v4/ [2/N] (#43039)
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
|
2026-05-18 21:00:58 -07:00 |
|
|
Nicolò LucchesiandNick Hill
|
fba010dd74
|
[Bugfix][MRV2] Fix KVCache tensor explicit kernel_block_size dim (#42766)
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-05-18 20:25:41 -07:00 |
|
|
Ofir Zafrir
|
8f16c4a5c0
|
[BugFix][CPU][Spec Decode] Fix Eagle implementation on CPU backend (#42468)
Signed-off-by: Ofir Zafrir <ofir.zafrir@intel.com>
|
2026-05-19 03:16:07 +00:00 |
|
|
haosdent
|
0191354827
|
[Perf][MLA] Enable FULL cudagraph capture for TRITON_MLA decode (#42885)
Signed-off-by: haosdent <haosdent@gmail.com>
|
2026-05-18 14:29:10 -07:00 |
|
|
Ronen Schaffer
|
84747489de
|
Tier offload followup (#42529)
Signed-off-by: Ronen Schaffer <ronen.schaffer@ibm.com>
|
2026-05-18 19:41:58 +00:00 |
|
|
Wentao Ye
|
e26736973a
|
[Model Runner V2] Fix prompt logprobs calculation Sizes of tensors must match error (#42778)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-05-18 08:27:21 -07:00 |
|
|
Netanel Haber
|
47829b1159
|
[Bugfix] mamba: run single-token extends as decodes (#42430)
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
|
2026-05-18 15:26:00 +00:00 |
|
|
Michael GoinandClaude Opus 4.7
|
f5d3dc7115
|
[Model Runner v2] Support update_config (#42783)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-05-18 10:26:07 -04:00 |
|
|
roikoren755
|
737bfa3a43
|
[Bugfix][Hybrid][NemotronH] Fix mamba_cache_mode=all + speculative decoding crash (#41233)
Signed-off-by: Roi Koren <roik@nvidia.com>
|
2026-05-18 14:54:00 +03:00 |
|
|
Tony LinandLi, Jiang <jiang1.li@intel.com>
|
965d076148
|
[CPU] Specify required KV cache layout for CPU attention backend (#42740)
Signed-off-by: Tony Lin <tony.lin@intel.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
|
2026-05-18 17:38:54 +08:00 |
|