Commit Graph

Select branches

Hide Pull Requests

dsv41-pd

dsv41-pd-visioncp

main

Mono Color

• c2ac37dbcc [Bug] ngram verify: keep batch.seq_lens_sum in sync after accept (#26753) Liangsheng Yin 2026-05-29 18:00:11 -07:00
• 95cd2fd29f [lora] More efficient pinned memory (#20876) Erik Wijmans 2026-05-29 17:04:59 -07:00
• a5e6a8887a [attention] Fallback to Triton merge_state when FlashInfer hits CUDA thread limit (#23993) Bruce Changlong Xu 2026-05-29 16:30:49 -07:00
• 6ea69efb7f [RL] Forward Kimi K2.5 weight hooks to language model (#26744) Byron HsuandByron Hsu 2026-05-29 15:08:58 -07:00
• 6ce49e5f4c [Utils] Support configure log level at runtime (#26583) Chao Shi 2026-05-30 05:49:06 +08:00
• cf66693b35 [Model] Add Qwen3-MoE MTP (#26468) 4 people 2026-05-29 14:31:05 -07:00
• 4ff1296f5e Optimize get load calls (/v1/loads) using shared-memory load snapshots (#26348) Lianmin Zhengandcctry 2026-05-29 13:40:26 -07:00
• 3cecc77ccb [perf] Fuse NVFP4 gate_up_gemm + swiglu + output FP4 quant (#26626) Qiaolin Yu 2026-05-29 13:16:24 -07:00
• 6b5f0d0ccb [core] Make spec_v2 seq_lens_cpu optional via backend needs_cpu_seq_lens; Triton opts out (#26128) Liangsheng YinandQiaolin-Yu 2026-05-29 13:00:32 -07:00
• ff8ed7a302 [refactor] unify cuda-graph capture/replay across attention backends (#26665) Cheng WanandClaude Sonnet 4.6 2026-05-29 12:46:42 -07:00
• 7fb7b41a3e [docs] Qwen3.5 cookbook: multi-node, MTP TP overrides, dense mamba flag (#26695) 3 people 2026-05-29 12:10:14 -07:00
• f113ece5cc Revert "improve: combine vit calls for images from different reqs from one batch (#25910)" (#26442) Bingxu ChenandCursor Agent 2026-05-30 02:13:34 +08:00
• ec075d8bc5 Fix DRAFT_EXTEND_V2 CG metadata: align test fixture and Triton with production seq_lens convention (#26651) Cheng WanandClaude Sonnet 4.6 2026-05-29 02:46:45 -07:00
• eb5d4827e8 [UnifiedTree]: Split unified tree kl ci into multiple files to reduce GPU usage. (#26666) Zhangheng 2026-05-29 17:46:34 +08:00
• 4585f8eb95 [refactor] remove unused op_mlp (#26673) akhoroshev 2026-05-29 16:38:56 +07:00
• 8652001b6a fix: use req.req_pool_idx instead of loop variable for req_to_token i… (#26534) chenxb002andkjuuii 2026-05-29 17:34:42 +08:00
• ed85bcf8c3 pin kernels<0.15 (#26704) Liangsheng Yin 2026-05-29 01:46:57 -07:00
• 544f3039d5 [PD] Fix IB device validation for JSON mappings (#26114) Teng Ma 2026-05-29 16:44:49 +08:00
• 9062f583db [ROCm] Eliminate redundant contiguous copy in MLA attention on ROCm MXFP4 (#25463) Rita Brugarolas 2026-05-29 01:28:32 -07:00
• 05bef58297 [Misc] Tiny change default building branch of sgl-deep-gemm (#26699) Baizhou Zhang 2026-05-29 01:18:36 -07:00
• 3e8d8736c8 fix stage-b-test-2-npu-a2 image (#26698) monkeyLoveding 2026-05-29 16:09:52 +08:00
• a722b1a437 [CPU] fix incorrect index of b_ptr in fused_sigmoid_gating_delta_rule… (#26634) blzheng 2026-05-29 16:08:12 +08:00
• 3ecf2c76ad [CPU] Add GPT-OSS model optimization for CPU (#16775) 3 people 2026-05-29 16:05:26 +08:00
• 5601b7139d [core] Make overlap-schedule WAR barrier CUDA-only (#26646) Bingxu Chen 2026-05-29 16:02:31 +08:00
• 4d1163e6a9 [PD][MoRI] Align hybrid state transfer with per-component schema (#26539) Niko Ma 2026-05-29 15:54:46 +08:00
• a42a7654a2 Update MooncakeStore batch tests to use v1 APIs (#25880) Chizheng Fang 2026-05-29 15:18:05 +08:00
• ace730db48 [AMD] Work around HIP TPOT regression from Event.wait() in MTP seq lens resolution (#26672) Arik 2026-05-29 15:18:02 +08:00
• 6e9bd82714 [AMD][CI] Update v4 CI setting and move the task to main branch (#26662) Thomas Wang 2026-05-29 15:12:40 +08:00
• b2eed9e16d [Apple Silicon] Add custom Metal RoPE kernel with fused KV cache store (#22868) Aditya SharmaandXiaodong Ye 2026-05-29 12:39:33 +05:30
• 7dff4118b9 Ignore .humanize folder (#26680) Jiajun LiandJiajun Li 2026-05-29 00:09:21 -07:00
• 08ec19872c [HotFix][Ling 2.6] Fix HybridLinearAttn dispatcher for Ling-2.6 (#26474) Yuan Luoandluoyuan.luo 2026-05-29 14:50:15 +08:00
• 0fb0ea7aac test: add trtllm_mha EAGLE-draft CG runner coverage (chain) (#26669) Cheng WanandClaude Sonnet 4.6 2026-05-28 23:46:06 -07:00
• 69362cbc2c [Doc] Update benchmark instruction for dsv4 (#26668) Baizhou Zhang 2026-05-28 23:37:35 -07:00
• 5850aa14c3 fix(mooncake): honour MOONCAKE_PROTOCOL so EFA hardware can select efa transport (#25083) 王鹤男andwhn09 2026-05-29 14:21:15 +08:00
• 73c99e3361 Ensure multi-node MM embedding cache consistency in insert_batch (#25959) 4 people 2026-05-29 13:59:46 +08:00
• 2dfbc3d781 test: strengthen CG-replay coverage with prod-fill padding, metadata invariants, and pad-ratio sweep (#26658) Cheng WanandClaude Sonnet 4.6 2026-05-28 22:43:29 -07:00
• 226649e3b7 [Fix] Fix FP8 Online Quantization (#26415) Colin Zandyichiche@amd.com 2026-05-28 22:00:09 -07:00
• f16816f043 fix: copy seq_lens in TRTLLM MHA draft decode cuda graph capture (#26521) Yongji Wu 2026-05-28 21:55:33 -07:00
• b47366fbf9 [NPU]: Optimize xgrammar token bitmask on NPU with AscendC (#24133) yuefeng Wu 2026-05-29 12:38:06 +08:00
• fba083c80f [CI] Split PP tests into base and extra suites (#26648) Shangming Cai 2026-05-29 12:15:27 +08:00
• 40f91e6697 [Bugfix] [DSA] [Hisparse] Broadcast TP Rank 0 Topk Indexes to other TPs (#24654) 3 people 2026-05-29 12:14:46 +08:00
• 84698b21e7 rename unittest as unittests (#26654) Cheng Wan 2026-05-28 21:14:06 -07:00
• 3ea9607d1c [diffusion] model: update to new model format (#26492) Dawid Majchrowski 2026-05-29 06:08:45 +02:00
• 621a79728c test: stabilize Gemma4 26B-A4B MTP GSM8K test with deterministic inference + tuned threshold (#26653) Khoa PhamandCursor 2026-05-28 20:58:48 -07:00
• dc4e7bc479 Fix TRTLLM MHA draft decode cache seqlens replay (#26655) Lianmin Zheng 2026-05-28 20:58:16 -07:00
• 79c844527c Upgrade xgrammar to 0.2.1 (#25676) Xinyuan Tong 2026-05-29 04:40:07 +01:00
• 272066566f [AMD] Pin compressed-tensors<0.16.0 for srt_hip (fixes ROCm 7.2 nightly build) (#26591) YC Yen-Ching Tseng 2026-05-29 11:34:45 +08:00
• b1173c8c14 [NPU] Enhance accuracy for model Step3_5 from 0 to 88% (#24582) McZyWu 2026-05-29 11:29:30 +08:00
• 36d0a6e08e [EPD] Optimize the Mooncake backend (#22587) LucQueenandZhengWG 2026-05-29 10:42:24 +08:00
• 569ee93357 [AMD] ci: switch CACHE_HOST to a fresh path to fix "No space left on device" (#26642) Michael 2026-05-29 10:40:54 +08:00
• 7619e77b7b [NPU] chore: basic software upgrade (#26466) monkeyLoveding 2026-05-29 10:04:15 +08:00
• 54b06f199c [lora] Share MoE LoRA Info (#24160) Erik Wijmans 2026-05-28 19:01:47 -07:00
• e381312664 Revert "Fix FA DRAFT_EXTEND_V2 cache extent" (#26628) Cheng WanandClaude Sonnet 4.6 2026-05-28 18:45:33 -07:00
• 0f8104ef15 [XPU] Fix Device Assignment (#26257) Rohit Kumar Singh 2026-05-29 07:08:11 +05:30
• 6258947039 NPU Nightly Pipeline Skip Test Case Adaptation and Recovery Testing (#26353) liuxianglong17 2026-05-29 09:29:25 +08:00
• 1c2857b064 bugfix: --decrypted-draft-config-file not applied (#25960) McZyWu 2026-05-29 09:15:05 +08:00
• fffdfb6fcb [Fix][NPU] Preserve existing packed_modules_mapping when merging model-level fused module mappings (#25755) Kurkur 2026-05-29 09:11:36 +08:00
• a8cfae0b30 doc: update step-3.7-flash docker image tag (#26625) Yuhao Yang 2026-05-29 08:40:17 +08:00
• f66f56c6bd Add attention-backend unit-test suite under test/registered/attention/unittest (#26517) Cheng WanandClaude Opus 4.7 2026-05-28 17:30:31 -07:00
• 3bdea78ad1 model: support Step-3.7-Flash (#26565) 3 people 2026-05-29 08:00:54 +08:00
• 0597242797 [CI] /rerun-test: descend into directories that a glob matched (#26614) Alison Shao 2026-05-28 16:52:42 -07:00
• 407106300e test/disaggregation: dp-attention keeps total_tokens e2e, simpler LB algos -> unit tests (#26617) Liangsheng Yin 2026-05-28 16:50:46 -07:00
• 3e255fd493 fix: Graceful fallback to CustomAllReduce when full_nvlink is not True (#25650) Yujun Dong 2026-05-29 07:28:33 +08:00
• 4f92e63c99 Let unittest._ShouldStop propagate through retry() so subTest+failfast works (#26616) Cheng WanandClaude Opus 4.7 2026-05-28 16:26:17 -07:00
• ec78fa6518 test/registered: cleanup pure model e2e tests (moves, splits, dedup, kit) (#26610) Liangsheng Yin 2026-05-28 15:41:46 -07:00
• 435c4ffb30 [CI] Clean DeepSeek V4 tests and installation scripts (#26609) Baizhou Zhang 2026-05-28 15:22:59 -07:00
• f838adb7d4 bench_serving: add Zipfian shared-prefix sampling to generated-shared-prefix (#26378) Jimmy Shong 2026-05-28 14:39:46 -07:00
• 97d129f8c6 # feat(bench): add SPEED-Bench dataset support to bench_serving (#24149) 3 people 2026-05-29 00:37:00 +03:00
• cd65be98df [CP] Add back qwen 30b test (#26604) Baizhou Zhang 2026-05-28 14:34:41 -07:00
• 93445e6359 [spec decoding] support kimi-k2.6-eagle3.1-mla draft (#26506) Khoa PhamandCursor 2026-05-28 14:26:39 -07:00
• 68706e615a [SPEC] fix: use effective max draft tokens for adaptive spec initiali… (#26354) shuwennandmaodoudou168 2026-05-29 04:33:11 +08:00
• 3ca8cb470f [BugFix] preserve cached token details in multi-tokenizer output (#26590) Cameron Quilici 2026-05-28 15:31:55 -05:00
• 690d4cdd94 Revert "[CI] FA3: ascending cuda-graph capture to avoid varlen workspace IMA (#26532) (#26550)" (#26600) Mohammad Miadh Angkad 2026-05-29 04:17:37 +08:00
• a38620b92c chore: add @pyc96 as codeowner for gemma4 files (#26601) Khoa Pham 2026-05-28 12:37:50 -07:00
• 34ea682a07 [UnifiedTree] gate load back pre-evict on full-attn availability only (#26302) Vladislav Nosivskoy 2026-05-28 19:30:03 +03:00
• e33bbbb467 [5/N] Quantization Refactor: GPTQ schemes and kernel split (#26402) Yaochen Hanandronnie_zheng 2026-05-28 22:15:16 +08:00
• d616b8edad [diffusion][jit_kernel] perf: varlen FA fast path for USPAttention masked branch (#26318) mispa-ms 2026-05-28 06:26:09 -07:00
• be32df33b9 [MUSA] Fix startup with patched torchada (#26437) 3 people 2026-05-28 20:57:55 +08:00
• f4eac50389 Fix GemmaRMSNorm gemma_weight buffer storage for Qwen3.5 (#26430) Jiajun Li 2026-05-28 03:42:46 -07:00
• 8e0ed75f2d Remove dead fields and always-False plumbing across SB / FB / LogitsMetadata (#26551) Liangsheng Yin 2026-05-28 03:15:04 -07:00
• f143d54d78 Add env-var-conventions skill (#26553) Liangsheng Yin 2026-05-28 02:58:37 -07:00
• c397a21167 [Ascend NPU] Enable GLM-4.6V series models inference (#26146) syy-hw 2026-05-28 17:27:12 +08:00
• bdfd5da53e [AMD] AITER Upgrade (#26562) Bingxu Chen 2026-05-28 17:04:58 +08:00
• 578d27e56a [bugfix] Honor cast_x_before_out_mul in RMSNorm.forward_cuda residual path (#25920) Xingyu Liu 2026-05-28 01:22:46 -07:00
• 12e28bdf0c Fix FlashInfer SWA EXTEND-with-prefix correctness in merge_state path (#26513) Cheng WanandClaude Opus 4.7 2026-05-28 01:16:58 -07:00
• 00cd6fb3d9 Add sliding-window mask support to TorchNativeAttnBackend (#26516) Cheng WanandClaude Opus 4.7 2026-05-28 01:06:57 -07:00
• a245cae3d1 [NPU] fix model ERNIE-4.5-21B-A3B-PT bias need 1D error (#26038) ZeyuanChen2000 2026-05-28 16:05:39 +08:00
• 8ca09a30f1 Allow Optional key/value in unified_attention_with_output split-op (MLA absorb fix) (#26515) Cheng WanandClaude Opus 4.7 2026-05-28 01:04:07 -07:00
• b429a30428 Expose Flex attention causal/decode masks as static methods (#26514) Cheng WanandClaude Opus 4.7 2026-05-28 01:03:32 -07:00
• e5f5d84780 Fix FA DRAFT_EXTEND_V2 cache extent (#26512) Cheng WanandClaude Opus 4.7 2026-05-28 00:56:23 -07:00
• 770c51b127 [Bug] Forward fixed_split_size in SWA / cross-attention paths of FlashInfer backend (#26412) Xingyu Liu 2026-05-28 00:52:26 -07:00
• 8dca6291c7 [CI] FA3: ascending cuda-graph capture to avoid varlen workspace IMA (#26532) (#26550) Liangsheng Yin 2026-05-28 00:50:35 -07:00
• 8f21b3e2ef [Refactor] JIT kernel benchmark (#25274) DarkSharpnessandClaude Opus 4.7 2026-05-28 15:49:55 +08:00
• 794fdd39ef fix: adapt dots_vlm for transformers v5 (#25829) hanwlax 2026-05-28 15:26:13 +08:00
• 50e0b3b77f Support Flashinfer Cute-DSL MLA attention (#24737) Brayden Zhongandb8zhong 2026-05-28 00:21:32 -07:00
• e31ea50df8 Remove DeepGEMM for indexer GEMM in piecewise NSA path (#26494) Brayden Zhongandb8zhong 2026-05-28 00:15:23 -07:00
• 686ef50672 Group ScheduleBatch and ForwardBatch fields by data-flow role (#26022) Liangsheng Yin 2026-05-28 00:11:20 -07:00
• b4808d44da Use Cute-DSL MXFP8 quantize kernels (#25486) Brayden Zhongandb8zhong 2026-05-28 00:01:31 -07:00
• 97dd6aad60 Add a little env var for disabling Flashinfer autotune cache (#26193) Brayden Zhong 2026-05-27 23:59:59 -07:00
• bed20249f1 fix(tool_call): reland schema type normalization (#26433) Xinyuan Tong 2026-05-28 07:31:18 +01:00