Commit Graph
54 Commits
Author SHA1 Message Date
Michael 05817a40c9 [AMD] Fix GLM-5.3 quark MoE MI35x test runner config (#41464) 2026-09-29 16:46:52 +08:00
7889fbab9a [PD] Keep EAGLE DP graph and token metadata consistent (#32196)
Co-authored-by: weireweire <20922698+weireweire@users.noreply.github.com>
Co-authored-by: Po-Han Huang (NVIDIA) <53919306+nvpohanh@users.noreply.github.com>
Co-authored-by: Khoa Pham <khoa.pham@radixark.ai>
2026-09-28 17:15:51 -07:00
YAMY f209e67767 [Spec] Model-agnostic last-stage draft embedding under pipeline parallelism (#39643) 2026-09-28 10:22:40 -07:00
Rain Jiang 6c4f36e47a Rust server unify datapath for mm and generate requests (#39679) 2026-09-27 23:36:07 -07:00
78eee88113 [Spec] Add LiLiCorr: a candidate-lattice reranker for DFlash drafts (#37462)
Co-authored-by: Po-Han Huang (NVIDIA) <53919306+nvpohanh@users.noreply.github.com>
Co-authored-by: kpham-sgl <khoa.pham@radixark.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-09-27 15:36:48 -07:00
Khoa Pham 7bdd8fe6ec [CI] Merge the Kimi-Linear PD DCP4 nightly tests and drop exact-token parity (#41321) 2026-09-26 09:48:00 -07:00
Sundara Raman Ramachandran 3ed56a341b [Score API] Setwise scoring: CausalLM support (batched + --enable-mis) (#41188) 2026-09-25 23:02:44 -07:00
Mohammad Miadh AngkadandMohammad Angkad 4bb645b8e2 [DSA] Fix the pooled-indexer breakable prefill bridge under DP attention (#41311)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-25 22:52:22 -07:00
Xiaoyu Zhang 38ec649048 [Refactor] Restore logical kernel groups and test organization (#41243) 2026-09-26 12:30:44 +08:00
Liangsheng Yin 516ab77619 [Test] Route all sgl-eval benchmarks through run_sgl_eval and deprecate run_eval (#41280) 2026-09-25 15:48:38 -07:00
Liangsheng Yin f88572a57c [Test] Add in-process sgl-eval adapter and move validated GSM8K tests to it (#41216) 2026-09-25 13:59:17 -07:00
Mohammad Miadh AngkadandMohammad Angkad 3fc7a669bf [CI] Move GLM-5.2 layer-split test to extra-b-test-8-gpu-b300 (#41207)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-24 21:25:48 -07:00
Sundara Raman Ramachandran 2f2f9d12f8 [Score API] Setwise Scoring Support (#38965) 2026-09-24 16:50:58 -07:00
3177d10ca6 Refactor the Cute-DSL AR fusion to support DeepseekV2 archs (GLM-5.3, etc.) (#39816)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
Co-authored-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
2026-09-24 06:00:58 -07:00
Mohammad Miadh AngkadandMohammad Angkad 86cb4a0f97 [CI] Update GLM-5.3-Flash H200/B200 test args (#40862)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-22 23:21:04 -07:00
Liangsheng Yin 78980a3b0b [misc] Remove deprecated endpoints, env vars and aliases past two releases (#40795) 2026-09-22 18:14:45 -07:00
Liangsheng Yin d34f7b2326 [mem_cache] Clean up SWA/Mamba radix cache leftovers and drop SGLANG_ENABLE_UNIFIED_RADIX_TREE (#40780) 2026-09-22 15:40:57 -07:00
Pei Li 66454d704b [Feature] Support --tokenizer-worker-num > 1 in the offline Engine API (#40260) 2026-09-22 10:50:01 -07:00
b44e248682 [AMD] [GLM-5.3-Flash Day 0] Enable FP8 and Quark MXFP4 MoE on gfx950 (#38546)
Co-authored-by: Raiden-Makoto <Raiden-Makoto@users.noreply.github.com>
Co-authored-by: Thomas Wang <thomawan@amd.com>
Co-authored-by: andyluo7 <andy.luo@amd.com>
Co-authored-by: Kevin Mi <mikevin920@yahoo.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-21 21:07:37 -07:00
Cheng Wan 506698761d [unified-memory] Hierarchical cache for every unified pool shape (#37507) 2026-09-21 16:50:37 -07:00
Cheng Wan 2d0e94e3a3 Check the topology identities where the layout is written, and build at the published widths (#40340) 2026-09-21 12:22:59 -07:00
Liangsheng Yin acd20a516e [CI] Give the kernel lane a 5090 suite and move kernel-only tests off the general lane (#40496) 2026-09-20 16:46:53 -07:00
Liangsheng Yin f6483e479f [Test] Drop cause-less disabled tests, fix XPU lane, demote quality gates off base-c (#40288) 2026-09-20 14:36:02 -07:00
amd-danli103andHAI e54009240a [AMD][DSV4] feat: enable DSpark with fp8 unified_kv on gfx950 (#38901)
Co-authored-by: HAI <hixiao@gmail.com>
2026-09-20 01:16:39 -07:00
metamergebotandcctry 9e5a62a767 [Logprob] Serve input-logprob temporaries from CUDA-graph-pool dead space (#40038)
Co-authored-by: cctry <csycfl@gmail.com>
2026-09-19 12:03:52 -07:00
Liangsheng Yin d507accadc [Test] Drop dead and strictly-subsumed CI test registrations (#40264) 2026-09-18 17:49:13 -07:00
Sam (Kesen Li) d346b214fb feat(kv-cache): support SM100 NVFP4 GenMHA and speculative decoding (#36340) 2026-09-18 14:50:46 -07:00
Ke BaoandSam Shleifer fd6f96bf96 Re-land dp-attention local control broadcast test (#39835)
Co-authored-by: Sam Shleifer <sshleifer@gmail.com>
2026-09-17 14:33:25 +08:00
25ce8063f7 Pipeline parallelism x speculative decoding (EAGLE/MTP) compatibility (#30775)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: YAMY1234 <74099316+YAMY1234@users.noreply.github.com>
Co-authored-by: Yangmin Li <yangminl@nvidia.com>
2026-09-16 21:41:54 -07:00
Qiaolin Yu 43390f63f5 [qwen 3.8 next] change the testing model in test_qwen4_exp_models.py (#39662) 2026-09-16 12:47:45 -07:00
Ke Bao 5aaa18207c Revert "[CI] Add e2e test for dp-attention local control broadcast" (#39828) 2026-09-16 23:41:50 +08:00
76e06febab [CI] Add e2e test for dp-attention local control broadcast (#39437)
Co-authored-by: Sam Shleifer <sam@thinkingmachines.ai>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-16 18:11:40 +08:00
Cao E f11cd8ab0e [XPU] Use torch scaled_mm for XPU block FP8 linear (#35605) 2026-09-16 10:10:31 +08:00
Yanbin Jiang ebd37705e4 [PD][LoRA] Gate decode admission on adapter slots (#39332) 2026-09-15 13:11:04 +08:00
amd-danli103 5aa9b8fb3e [AMD][DSV4] feat: enable fp8 two-pool unified_kv on gfx950 (#37413) 2026-09-14 02:49:11 -07:00
Cheng Wan 6410800af9 [unified-memory] Enable prefill cuda-graph capture (#37418) 2026-09-13 19:17:19 -07:00
Cheng Wan 2ec4bbcbd4 [unified-memory] PD disaggregation for every unified pool shape (#37506) 2026-09-13 19:16:43 -07:00
desmond-intel 6dc7b3421b Inference Support Mamba 2 and 1 (#34556) 2026-09-12 20:51:18 +08:00
Yanbin JiangandShuwen Wang 0b415fa573 [HiCache][LoRA] Isolate storage pages by extra key (#38577)
Co-authored-by: Shuwen Wang <47200617+alphabetc1@users.noreply.github.com>
2026-09-12 18:18:14 +08:00
FrancisandQiaolin-Yu e91c948057 feat: support TP>1 Domino rollout for DFlash V2 (#37069)
Co-authored-by: Qiaolin-Yu <liin1211@outlook.com>
2026-09-11 18:51:11 -07:00
a207786205 [PD] Transfer the DCP-replicated DSPARK draft KV in DCP1->DCP-N relayouts (#37709)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-11 17:15:18 -07:00
Yanbin Jiang ec30f19e4a [LoRA] Support MoE in full and breakable prefill CUDA graphs (#38578) 2026-09-11 14:40:02 -07:00
MickandMick Qian 358c163250 [diffusion] fix: recover ipc jit initialization after interrupted builds (#39034)
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
2026-09-11 19:34:09 +08:00
Mohammad Miadh AngkadandMohammad Angkad ad5af539cd [CI] Trim DSV4 trtllm B200 tests (#39013)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
2026-09-11 01:04:16 -07:00
ANSHUMAN TRIPATHYandMa Mingfei 0fadad8933 DFLASH support added for XPU (#32798)
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
2026-09-11 10:39:37 +08:00
ANSHUMAN TRIPATHY 3716e496ea Speculative Decoding support for intel_xpu attention backend on XPU target (#30548) 2026-09-11 10:25:25 +08:00
DAI0818andPo-Han Huang 03e4c06589 Fix Qwen3.5 GDN multi-item scoring (#33922)
Co-authored-by: Po-Han Huang (NVIDIA) <53919306+nvpohanh@users.noreply.github.com>
2026-09-09 22:30:39 -07:00
880d6fa64d [DSv4] Integrate TRT-LLM DSv4 Attention for SM100/103 (#30805)
Co-authored-by: Yangmin Li <yangminl@nvidia.com>
Co-authored-by: Po-Han Huang (NVIDIA) <53919306+nvpohanh@users.noreply.github.com>
2026-09-09 17:40:07 -07:00
FrancisandQiaolin-Yu a84ffd1326 feat: add optimized Domino rollout to DFlash V2 (#36899)
Co-authored-by: Qiaolin-Yu <liin1211@outlook.com>
2026-09-09 14:12:15 -07:00
Alison ShaoandClaude Opus 5 95a88bfd69 Relax GSM8K thresholds for the GLM-5.2 DSA-MTP variants (#38725)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-09 12:46:10 -07:00