Commit Graph
2631 Commits
Author SHA1 Message Date
Ma Mingfei 821d5f4a5b [CPU] add faster KV-cache writes (#25874) 2026-05-25 10:28:52 +08:00
Liangsheng Yin d7e3e54148 [Test] split test/registered/distributed/ into topic folders (#26240) 2026-05-24 17:02:07 -07:00
Liangsheng Yin 030bd5d3ed [Test] test_session_latency: assert streaming tail/head stability (#26230) 2026-05-24 14:06:41 -07:00
shuwenn 36eb72bf12 [UnifiedTree] fix: backup SWA-split parent before child under write-through (#25065) 2026-05-25 00:21:57 +08:00
Dongjun Na 9d50cd9742 [observability] add ServerArgs.stat_loggers for pluggable metrics backend (#24610)
Signed-off-by: Dongjun Na <kmu5544616@gmail.com>
2026-05-24 22:41:28 +08:00
Mick b6f71d5850 [VLM] avoid extra cuda-ipc staging for preprocessed input (#26096) 2026-05-24 19:48:06 +08:00
Khoa PhamandClaude Opus 4.7 b0ce16d0c5 [CP] 1/N: Support MLA Prefill Context Parallel (#23292)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-23 03:07:09 -07:00
liuxianglong17 8c78424701 Reduce excessively long logs caused by transformer version updates. (#26033) 2026-05-23 17:12:08 +08:00
Baizhou Zhangandyhyang201 7b7f1067bd Add non-MTP DSV4 test coverage (#26141)
Co-authored-by: yhyang201 <yhyang201@gmail.com>
2026-05-22 19:43:17 -07:00
weireweire 629b6c6a85 correct allreduce fusion and dummy_run alignment in SCATTERED MLP mode (moe_dense_tp_size=1) (#19918) 2026-05-22 19:18:25 -07:00
nvjullin cadfa2d025 Support piecewise CUDA graph with NSA (#23351) 2026-05-22 14:39:50 -07:00
Kangyan-ZhouandClaude Opus 4.7 085777210c feat(kv-events): expose structured KV-event publisher block on /server_info (#25844)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-23 01:59:45 +08:00
Jialin Ouyangandjialino 06c23d55b5 perf: migrate Req token-id storage to array.array('q') in Scheduler (#25098)
Co-authored-by: jialino <jialino@fb.com>
2026-05-22 10:51:07 -07:00
zhangtao2-1andzhangtao 6baa859a86 Add MiniCPM5 tool call parser for XML-style function calls (#25600)
Co-authored-by: zhangtao <zhangtao2@modelbest.cn>
2026-05-22 23:09:40 +08:00
Cheng WanandClaude Sonnet 4.6 d765dfd043 refactor(attn): init hisparse_coordinator before attn_backend; replace lazy property with init-time capture (#26012)
Co-authored-by: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
2026-05-21 16:03:42 -07:00
Cheng WanandClaude Sonnet 4.6 c5251a98a9 feat(model_runner): remove pool/backend refs from ForwardBatch via ForwardContext (#25983)
Co-authored-by: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
2026-05-21 14:01:49 -07:00
Shangming Cai fbebdd5105 [CI] Enable nixl disaggregation test for decode radix cache (#25990) 2026-05-21 19:29:24 +08:00
Xinyuan Tong 40faf44f7a [auto-detect] match Ring-2.6/Ling XML kv tool-call format via vocab signature (#25366) 2026-05-20 23:34:52 -07:00
Bingxu ChenandCursor Agent 45cadc215f [AMD][CI] Clean up AMD nightly + pr-test workflows (#25266)
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
2026-05-20 23:30:26 -07:00
Cheng WanandClaude Sonnet 4.6 888a8794ef [Fix] DSV4 cached_loc invalidated when SWA mapping is rebuilt (#25889)
Co-authored-by: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
2026-05-20 22:38:12 -07:00
84ea47eb22 [CPU] Fix issues when running llama3.2-11B vision model with image tasks (#8666)
Co-authored-by: JieXin Liang <Alcanderian@users.noreply.github.com>
Co-authored-by: Yineng Zhang <me@zhyncs.com>
Co-authored-by: jianan-gu <jianan.gu@intel.com>
2026-05-21 13:09:18 +08:00
Cheng WanandClaude Sonnet 4.6 79b937aefb [Refactor] Encapsulate SWA loc translation inside SWAKVPool with per-batch cache invalidation (#25824)
Co-authored-by: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
2026-05-20 21:26:32 -07:00
YC Yen-Ching Tseng 90efa9c83f [AMD] Fix AMD stage-a-test-small-1-gpu (#25932) 2026-05-20 20:51:49 -07:00
Randall LinandCursor 791a2f057f Add overridable hooks for custom chat serving implementations (#25807)
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-05-21 11:21:25 +08:00
Kevin Flansburg 643d44d699 [BugFix] fix(hicache): fix two slot-reuse races in DecodeKVCacheOffloadManager (#24226) 2026-05-20 18:20:19 -07:00
Yuzhen Zhou dac78768f0 [RL][TITO] Preserve whitespace in reasoning parser outputs (#24251) 2026-05-20 19:45:09 +00:00
Ratish P 5e7bf73757 Fix bench_serving non-stream reasoning content (#25298) 2026-05-20 18:41:46 +00:00
Jialin Ouyang 6e0b7f35ad [radix cache] pluggable RadixCache factory (--radix-cache-backend) (#25101) 2026-05-20 10:05:04 -07:00
Liangsheng Yin 1bd4f94598 [Test] Add fwd_occupancy sanity kit (#25886) 2026-05-20 03:34:37 -07:00
Liangsheng Yin 614672fea5 [Test] Stage-a sanity kits; consolidate core/ + models_e2e/ tests (#25831) 2026-05-20 01:58:48 -07:00
Yuhong Guo 24d27c2035 [BugFix] Fix rid_to_state leak for aborted queued requests (#24070) 2026-05-20 01:32:44 -07:00
044649c23a feat: Support flashinfer_cutedsl MoE runner with flashinfer alltoall backend (#22669)
Co-authored-by: Trevor Morris <tmorris@nvidia.com>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-20 00:36:26 -07:00
Cheng WanandClaude Sonnet 4.6 8131641bc6 [Refactor] Rename NSA → DSA: user-facing aliases, file/class/import rename (#25821)
Co-authored-by: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>
2026-05-20 00:18:04 -07:00
liuxianglong17andAdarsh Shirawalmath 579fed2090 Reduce excessively long logs caused by transformer version updates. (#25737)
Co-authored-by: Adarsh Shirawalmath <114558126+adarshxs@users.noreply.github.com>
2026-05-20 11:39:03 +08:00
Paiiiiandzengpai 425dffbde3 DeepSeek V4 MTP Support CP (#24934)
Co-authored-by: zengpai <zengpai@baidu.com>
2026-05-19 16:51:31 -07:00
b9d470f4a2 Support spec v2 for FlashMLA speculative decoding (#24640)
Co-authored-by: Jackey Hua <zhendonghua@users.noreply.github.com>
Co-authored-by: Depend <yu-depend@users.noreply.github.com>
2026-05-19 15:23:17 -07:00
Liangsheng Yin 2f70902329 deflake priority below-threshold test (#25809) 2026-05-19 15:19:01 -07:00
b9c2bf717b [BugFix] Resolve adaptive speculative decoding conflicts for Qwen3.5 (hybrid GDN) (#23331)
Signed-off-by: EanWang211123 <wangyiheng@sangfor.com.cn>
Co-authored-by: shuwenn <47200617+alphabetc1@users.noreply.github.com>
Co-authored-by: shuwenn <2508695655@qq.com>
2026-05-19 15:09:49 -07:00
Ratish P fab097d66d [Gemma4]: Fix FP8 Triton scale layout (#25286) 2026-05-19 14:00:23 -07:00
Yuan Luoandluoyuan.luo 4c0ce0345d Support Gemma4 Pipeline Parallelism (#25284)
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
2026-05-19 22:40:11 +08:00
67fd005b97 [HiSparse & PD] Support hisparse memory pool host page > 1 (#23606)
Co-authored-by: hzh0425 <hzh0425@apache.org>
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
2026-05-19 01:29:35 -07:00
Ziang Li 78cb38ed5e [FlashInfer v0.6.11] [RL] Support FlashInfer per-token NVFP4 MoE (#22918) 2026-05-19 01:04:48 -07:00
YC Yen-Ching Tseng 7c3f614e23 [AMD] Bump amd/Kimi-K2.5-MXFP4 revision to align with shared-experts fusion (#25740) 2026-05-18 22:47:05 -07:00
huangtingweiandhzh0425 c2a212bfe2 [UnifiedTree] Support DeepSeek V4 host pool with multiple layouts. (#25282)
Co-authored-by: hzh0425 <hzh0425@apache.org>
2026-05-19 09:36:00 +08:00
fzyzcjy 170fe57cf0 Encapsulate the pending-flush bookkeeping in a small wrapper (#25727) 2026-05-19 09:23:10 +08:00
fzyzcjy 3fd6a58e6c Inline the single-use split-prefill setup at its caller (#25722) 2026-05-19 09:21:29 +08:00
fzyzcjy fa37b68653 Rename the request mid-chunk flag to describe what it actually tracks (#25720) 2026-05-19 09:20:43 +08:00
fzyzcjy 954b5c5846 Pack scattered scheduler IPC channel state into a dedicated container (#25714) 2026-05-19 09:19:02 +08:00
Ratish P dbac464726 [Spec]: Make Triton standalone spec test deterministic (#25303) 2026-05-18 17:36:10 -07:00
Cheng Wan b7267e8fce [CI] Enable weight prefetch for 8-gpu-h200 basic tests (#25684) 2026-05-18 14:12:45 -07:00