Commit Graph
2036 Commits
Author SHA1 Message Date
Wei Zhao c3ec0d29f5 [Bugfix] Fix cuda profiler missing bug (#55237) 2026-09-07 03:15:57 +00:00
Kevin H. LuuandCodex 6865e67f0b [Bugfix] Defer adaptive verification until after kernel warmup (#55455)
Signed-off-by: khluu <khluu000@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
2026-09-06 11:31:40 -07:00
Kevin H. LuuandCodex 722d169339 [CI] Align extraction test with canonical auxiliary layer order (#55457)
Signed-off-by: khluu <khluu000@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
2026-09-06 11:22:14 -07:00
Almog TavorandOr Ozeri dc02934a07 [Bugfix][KV Offload] Stop offloading the final sampled token's KV slot (#54288)
Signed-off-by: almogtavor <almogtavor@gmail.com>
Signed-off-by: Almog Tavor <70065337+almogtavor@users.noreply.github.com>
Co-authored-by: Or Ozeri <or@ozery.com>
2026-09-06 15:22:19 +03:00
569adb5a97 [Bugfix][KV Offload] Fix SWA store reachability during chunked prefill (#54362)
Signed-off-by: Will Hampson <whamp@ggl.slmail.me>
Co-authored-by: Will Hampson <whamp@ggl.slmail.me>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
2026-09-06 13:50:39 +03:00
Zupeng WangandCodex dd0760165c [Bugfix] Fall back to T1 when ARC cannot reclaim enough entries from T2 (#55461)
Signed-off-by: Wang Zupeng <zupenwang@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
2026-09-06 13:28:19 +03:00
9afb878a55 [Bugfix][KV Offload] Skip cleaned-up async lookup batches (#55075)
Signed-off-by: Alex <jihui.huang@daocloud.io>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
2026-09-06 13:27:46 +03:00
Ziming HuangandOpenAI Codex 144e79c810 [Kimi K3] Support internal prefix checkpoints with partial prefix caching and spec-decoding (#53614)
Signed-off-by: Ziming Huang <zelda.huanghuang@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
2026-09-06 13:18:15 +08:00
aoshen02 039ea82660 [Core] Sync DP state on the first step of a wave (#52957)
Signed-off-by: aoshen02 <aoshen@inferact.ai>
2026-09-06 02:16:58 +00:00
d87a440f88 [Core][MRV2] Support eagle3 spec decode with pipeline parallel (#50514)
Signed-off-by: Yongqin Wang <yongqinwang@roblox.com>
Co-authored-by: Cursor <noreply@cursor.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
2026-09-05 11:45:34 +08:00
Andreas KaratzasandOpenAI Codex a7f9be9612 [CI][ROCm] Raise AMD job and server readiness timeouts (#55308)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
2026-09-05 10:50:51 +08:00
eb74fbb3e7 [Bugfix][NIXL] Don't assert when a failed transfer is cleaned up twice (#54518)
Signed-off-by: Yizheng Jiao <jyizheng@gmail.com>
Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: NickLucche <nicolo.lucchesi@mistral.ai>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
2026-09-04 23:20:32 +00:00
685074cd61 [Bugfix][V2] Warm up kernels before capturing CUDA graphs (#55341)
Signed-off-by: aoshen02 <aoshen02@users.noreply.github.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
2026-09-04 22:44:18 +00:00
3f41d102c5 [1/2][Model Runner V2] DBO support, eager mode (#50945)
Signed-off-by: specture724 <specture724@gmail.com>
Signed-off-by: Anjie Hou <149605198+specture724@users.noreply.github.com>
Co-authored-by: jiangkuaixue123 <jiangxiaozhou111@163.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
2026-09-04 14:17:39 -07:00
Stefano Castagnetta 2524051385 [Bugfix][Spec Decode] Honour the draft's attention_backend on Model Runner V2 (#54826)
Signed-off-by: Stefano Castagnetta <scastagnetta@nvidia.com>
2026-09-04 12:23:19 -07:00
Summer Yang 8cd95f7de7 [Bugfix][MLA] Restore DSpark cache-group capability under optimized Python (#55234)
Signed-off-by: Summer Yang <girasoleyang@gmail.com>
2026-09-04 10:24:31 -07:00
Qiming Zhang 07ee97e023 [Test] Split test_sampling_mask_preserves_top_k_boundary_ties to remove Triton-kernel-specific assumption Description (#55315)
Signed-off-by: mayuyuace <qiming1.zhang@intel.com>
2026-09-04 14:16:50 +01:00
Tony LinandKevin H. Luu 9cd956c7e6 [CI/Test] Add expert parallelism coverage to external LB tests (#53497)
Signed-off-by: Tony Lin <tony.lin@intel.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
2026-09-04 15:56:59 +08:00
YizhouandOpenAI Codex 8f816a3f66 [MRV2][Metrics] Support CUDAGraphStat in MRV2 (#52358)
Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
2026-09-04 07:19:50 +00:00
Ilya MarkovandBugen Zhao ae2d1ca96f [Rust Frontend] Record Mooncake/NIXL KV-connector metrics (#52755)
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Signed-off-by: Markov Ilya <markovilya197@gmail.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
2026-09-04 06:21:54 +00:00
Jeff (Junze) MaandOpenAI Codex e35298628f [Bugfix][KV Connector] Fix DecodeBenchConnector prefix block selection (#54878)
Signed-off-by: Jeff Ma <jeffjma@umich.edu>
Co-authored-by: OpenAI Codex <noreply@openai.com>
2026-09-04 04:05:58 +00:00
omerpaz95andClaude Opus 5 8a0a7ee40a [EC Connector] P2P NIXL + CPU EC Connector (#47941)
Signed-off-by: omerpaz95 <omerpaz95@gmail.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-09-04 11:23:56 +08:00
Ziming HuangandOpenAI Codex a26b71d868 [Bugfix][PD] Pad resumed speculative decode requests (#55126)
Signed-off-by: Ziming Huang <48115868+ZeldaHuang@users.noreply.github.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
2026-09-04 11:05:33 +08:00
bnellnmandTyler Michael Smith 25268f0c9c [KVConnector] Add retention interval to OffloadingConnector (#51886)
Signed-off-by: Bill Nell <bnell@redhat.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
2026-09-04 02:42:20 +00:00
guangli_LiuliuguangliOpenAI Codexmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
d9e2b5238d [Core][KV Events] Echo session_id on GPU BlockStored events (#51381)
Signed-off-by: liuguangli <liuguangli35@gmail.com>
Signed-off-by: jinx-machinepulse <2679622408@qq.com>
Co-authored-by: liuguangli <liuguangli35@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-09-04 02:22:50 +00:00
560ef78bfe [Perf][Model Runner V2] Compact sampling masks on GPU instead of unpacking the full-vocab bitmask on CPU (#54901)
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Signed-off-by: vx120 <893600387@qq.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: vx120 <893600387@qq.com>
2026-09-03 19:03:36 -07:00
Jiangyun Zhu 98ed0856f3 [Model] add GLM-5.3-Flash support (#53906) 2026-09-03 09:40:35 -07:00
Yifan Jiang da8ec28268 [Bugfix][KV Offload] Do not let a recurrent group's unhashed block truncate the load boundary (#52807)
Signed-off-by: Yifan Jiang <19356972+yifjiang@users.noreply.github.com>
2026-09-03 19:08:46 +03:00
mevince 4ae6228284 [Bugfix][KV Connector] Populate SimpleCPUOffload BlockStored metadata (#54325) 2026-09-03 15:58:07 +00:00
Jeff (Junze) MaandOpenAI Codex 31e9c13685 [Bugfix][KV Connector] Safely fill circular buffers in DecodeBench (#54879)
Signed-off-by: Jeff Ma <jeffjma@umich.edu>
Co-authored-by: OpenAI Codex <noreply@openai.com>
2026-09-03 15:16:22 +00:00
Nick Hillandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com> bf95f58d10 [Core] Triton kernel for small-batch top-p only masking (#54651)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-09-03 07:52:47 -07:00
092334c828 [Bugfix] Wait for offload keys before storing chunks (#52923)
Signed-off-by: chuanzhisongshu <49055103+982945902@users.noreply.github.com>
Co-authored-by: lishuo121 <lishuo121@jd.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
2026-09-03 11:07:35 +03:00
Derek WeitzelandClaude Fable 5.1 859dd39512 [Bugfix][Core] Wait for the previous PP tensor sends before the next forward pass (#54962)
Signed-off-by: Derek Weitzel <djw8605@gmail.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-03 08:01:36 +00:00
waizuichougouandNick Hill 3f1af35e01 [Bugfix][Multimodal] Handle prefix-covered items in SHM worker cache (#54994)
Signed-off-by: waizuichougou <2082431897@qq.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
2026-09-03 06:39:34 +00:00
Isotr0py 1356635d83 [New model][Multimodal] Add DeepSeek-V4-Flash-Vision-Exp support (#54566)
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
2026-09-02 11:09:09 -07:00
Ilia Yastrebov 41848caa63 [NIXL] Use int32 array for indices to avoid intermediate conversion (#51952)
Signed-off-by: Ilia Yastrebov <iyastrebov@nvidia.com>
2026-09-02 16:30:16 +02:00
drakoshaandClaude ba6c60e98f [Bugfix][KV Offload] Scale UniformTypeKVCacheSpecs groups by DCP (#50883)
Signed-off-by: Mikhail Kostryukov <mike@triptrack.net>
Co-authored-by: Claude <noreply@anthropic.com>
2026-09-02 17:11:48 +03:00
AlexHuangandOpenAI Codex 35faf957d6 [Bugfix][KV Offload] Ignore stale async lookup results (#54872)
Signed-off-by: Alex <jihui.huang@daocloud.io>
Co-authored-by: OpenAI Codex <noreply@openai.com>
2026-09-02 17:10:26 +03:00
Tomasz Zielinskimergify[bot] <37929162+mergify[bot]@users.noreply.github.com>Claude Opus 5Harry Mellor
ffe3bb3c72 [Hardware][XPU] Register matmul and linear batch-invariant kernels for XPU (#49209)
Signed-off-by: tzielinski-habana <tomasz.zielinski@intel.com>
Signed-off-by: Tomasz Zielinski <85164140+tzielinski-habana@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2026-09-02 13:31:38 +00:00
Cheng RuiandCodex 2a4e3cc3db [Bugfix][KV Offload] Ensure tracker progress for oversized offers (#54759)
Signed-off-by: Cheng Rui <286040359@qq.com>
Co-authored-by: Codex <noreply@openai.com>
2026-09-02 14:09:29 +03:00
Kevin H. Luu 76ba32160a [CI] Shard CPU jobs above the 24h P90 threshold (#54751)
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com>
2026-09-02 02:16:05 -07:00
Andreas KaratzasandOpenAI Codex 87deddc7a4 [CI][Spec Decode] Add MTP placeholder-token regression coverage (#54893)
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
2026-09-02 03:29:38 -05:00
Itay EtelisItay EtelisOr Ozerimergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
df09c76735 [KV Connector][Offloading] Look through UniformTypeKVCacheSpecs in the canonical portability gate (#51690)
Signed-off-by: Itay Etelis <itay.etelis@ibm.com>
Co-authored-by: Itay Etelis <itay.etelis@ibm.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-09-02 10:43:26 +03:00
12b9573c98 [Bugfix][KV Offloading] Fix eager SimpleCPUOffload cache registration and final flush (#53532)
Signed-off-by: maithilijoshi20 <maithilijoshi2003@gmail.com>
Signed-off-by: maithilijoshi20 <97733343+maithilijoshi20@users.noreply.github.com>
Co-authored-by: maithilijoshi20 <maithilijoshi2003@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
2026-09-02 03:23:09 +00:00
Nick Hill a56e74afd6 [CI] Remove MRV2-specific tests (#54823)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
2026-09-01 14:15:12 -07:00
Jeff (Junze) MaandOpenAI Codex 18c53727ce [Bugfix][KV Connector] Fix DecodeBench DCP block selection (#54679)
Signed-off-by: Jeff Ma <jeffjma@umich.edu>
Co-authored-by: OpenAI Codex <noreply@openai.com>
2026-09-01 20:31:30 +00:00
Zhewen Liandzhewenl 5cc32fbdfa [Bugfix][KV Connector] Fix Mooncake physical-block transfer length (#54272)
Signed-off-by: zhewenl <zhewenl@users.noreply.github.com>
Co-authored-by: zhewenl <zhewenl@users.noreply.github.com>
2026-09-01 13:23:46 -07:00
7cb9a88f50 [Bugfix][Mooncake] Offload producer partial tails on request finish (#52832)
Signed-off-by: Dao Le <Dao007forever@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: OpenAI Codex <noreply@openai.com>
2026-09-01 13:23:35 -07:00
周峥andGuanyi Chen c866ba9d11 [KV Connector] Support heterogeneous TP sharing in Mooncake Store Connector (#53129)
Signed-off-by: Guanyi Chen <939416532@qq.com>
Signed-off-by: z-zanez <zhouzh93@mail2.sysu.edu.cn>
Signed-off-by: Zheng Zhou <zhouzh93@mail2.sysu.edu.cn>
Signed-off-by: zane <zhouzh93@mail2.sysu.edu.cn>
Co-authored-by: Guanyi Chen <939416532@qq.com>
2026-09-01 10:18:06 -07:00
Luke AlonsoandLucas Wilkinson 0d4ad47981 [Kernel] Add B12X causal paged attention backend (#52017)
Signed-off-by: Luke Alonso <lalonso@gmail.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
2026-09-01 10:42:02 -04:00