Qiaolin Yu
3cecc77ccb
[perf] Fuse NVFP4 gate_up_gemm + swiglu + output FP4 quant ( #26626 )
2026-05-29 13:16:24 -07:00
Liangsheng Yin and Qiaolin-Yu
6b5f0d0ccb
[core] Make spec_v2 seq_lens_cpu optional via backend needs_cpu_seq_lens; Triton opts out ( #26128 )
...
Co-authored-by: Qiaolin-Yu <liin1211@outlook.com >
2026-05-29 13:00:32 -07:00
Cheng Wan and Claude Sonnet 4.6
ff8ed7a302
[refactor] unify cuda-graph capture/replay across attention backends ( #26665 )
...
Co-authored-by: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com >
2026-05-29 12:46:42 -07:00
7fb7b41a3e
[docs] Qwen3.5 cookbook: multi-node, MTP TP overrides, dense mamba flag ( #26695 )
...
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-05-29 12:10:14 -07:00
Bingxu Chen and Cursor Agent
f113ece5cc
Revert "improve: combine vit calls for images from different reqs from one batch ( #25910 )" ( #26442 )
...
Co-authored-by: Cursor Agent <cursoragent@cursor.com >
2026-05-29 11:13:34 -07:00
Cheng Wan and Claude Sonnet 4.6
ec075d8bc5
Fix DRAFT_EXTEND_V2 CG metadata: align test fixture and Triton with production seq_lens convention ( #26651 )
...
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-05-29 02:46:45 -07:00
Zhangheng
eb5d4827e8
[UnifiedTree]: Split unified tree kl ci into multiple files to reduce GPU usage. ( #26666 )
2026-05-29 02:46:34 -07:00
akhoroshev
4585f8eb95
[refactor] remove unused op_mlp ( #26673 )
2026-05-29 02:38:56 -07:00
chenxb002 and kjuuii
8652001b6a
fix: use req.req_pool_idx instead of loop variable for req_to_token i… ( #26534 )
...
Co-authored-by: kjuuii <1375341936@qq.com >
2026-05-29 02:34:42 -07:00
Liangsheng Yin
ed85bcf8c3
pin kernels<0.15 ( #26704 )
2026-05-29 01:46:57 -07:00
Teng Ma
544f3039d5
[PD] Fix IB device validation for JSON mappings ( #26114 )
2026-05-29 16:44:49 +08:00
Rita Brugarolas
9062f583db
[ROCm] Eliminate redundant contiguous copy in MLA attention on ROCm MXFP4 ( #25463 )
...
Signed-off-by: Rita Brugarolas Brufau <rita.brugarolasbrufau@amd.com >
2026-05-29 01:28:32 -07:00
Baizhou Zhang
05bef58297
[Misc] Tiny change default building branch of sgl-deep-gemm ( #26699 )
2026-05-29 01:18:36 -07:00
monkeyLoveding
3e8d8736c8
fix stage-b-test-2-npu-a2 image ( #26698 )
2026-05-29 16:09:52 +08:00
blzheng
a722b1a437
[CPU] fix incorrect index of b_ptr in fused_sigmoid_gating_delta_rule… ( #26634 )
2026-05-29 16:08:12 +08:00
3ecf2c76ad
[CPU] Add GPT-OSS model optimization for CPU ( #16775 )
...
Co-authored-by: mingfeima <mingfei.ma@intel.com >
Co-authored-by: jianan-gu <jianan.gu@intel.com >
2026-05-29 16:05:26 +08:00
Bingxu Chen
5601b7139d
[core] Make overlap-schedule WAR barrier CUDA-only ( #26646 )
2026-05-29 01:02:31 -07:00
Niko Ma
4d1163e6a9
[PD][MoRI] Align hybrid state transfer with per-component schema ( #26539 )
2026-05-29 00:54:46 -07:00
Chizheng Fang
a42a7654a2
Update MooncakeStore batch tests to use v1 APIs ( #25880 )
...
Signed-off-by: fangchizheng <fangchizheng@mail.ustc.edu.cn >
2026-05-29 00:18:05 -07:00
Arik
ace730db48
[AMD] Work around HIP TPOT regression from Event.wait() in MTP seq lens resolution ( #26672 )
2026-05-29 00:18:02 -07:00
Thomas Wang
6e9bd82714
[AMD][CI] Update v4 CI setting and move the task to main branch ( #26662 )
2026-05-29 00:12:40 -07:00
Aditya Sharma and Xiaodong Ye
b2eed9e16d
[Apple Silicon] Add custom Metal RoPE kernel with fused KV cache store ( #22868 )
...
Signed-off-by: Xiaodong Ye <yeahdongcn@gmail.com >
Co-authored-by: Xiaodong Ye <yeahdongcn@gmail.com >
2026-05-29 15:09:33 +08:00
Jiajun Li and Jiajun Li
7dff4118b9
Ignore .humanize folder ( #26680 )
...
Co-authored-by: Jiajun Li <jiajun.li@MacBook-Pro-F7J34QJK2C-jiajunli.local >
2026-05-29 00:09:21 -07:00
Yuan Luo and luoyuan.luo
08ec19872c
[HotFix][Ling 2.6] Fix HybridLinearAttn dispatcher for Ling-2.6 ( #26474 )
...
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com >
2026-05-29 14:50:15 +08:00
Cheng Wan and Claude Sonnet 4.6
0fb0ea7aac
test: add trtllm_mha EAGLE-draft CG runner coverage (chain) ( #26669 )
...
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-05-28 23:46:06 -07:00
Baizhou Zhang
69362cbc2c
[Doc] Update benchmark instruction for dsv4 ( #26668 )
2026-05-28 23:37:35 -07:00
王鹤男 and whn09
5850aa14c3
fix(mooncake): honour MOONCAKE_PROTOCOL so EFA hardware can select efa transport ( #25083 )
...
Co-authored-by: whn09 <whn09@users.noreply.github.com >
2026-05-29 14:21:15 +08:00
73c99e3361
Ensure multi-node MM embedding cache consistency in insert_batch ( #25959 )
...
Signed-off-by: Michael Qiu <qiudayu.qdy@antgroup.com >
Co-authored-by: Mike_Qiu <qiudayu.qdy@antgroup.com >
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com >
Co-authored-by: siyu <liusy58@linux.alibaba.com >
2026-05-29 13:59:46 +08:00
Cheng Wan and Claude Sonnet 4.6
2dfbc3d781
test: strengthen CG-replay coverage with prod-fill padding, metadata invariants, and pad-ratio sweep ( #26658 )
...
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-05-28 22:43:29 -07:00
Colin Z and yichiche@amd.com
226649e3b7
[Fix] Fix FP8 Online Quantization ( #26415 )
...
Co-authored-by: yichiche@amd.com <jacky.cheng>
2026-05-28 22:00:09 -07:00
Yongji Wu
f16816f043
fix: copy seq_lens in TRTLLM MHA draft decode cuda graph capture ( #26521 )
2026-05-28 21:55:33 -07:00
yuefeng Wu
b47366fbf9
[NPU]: Optimize xgrammar token bitmask on NPU with AscendC ( #24133 )
2026-05-28 21:38:06 -07:00
Shangming Cai
fba083c80f
[CI] Split PP tests into base and extra suites ( #26648 )
...
Signed-off-by: Shangming Cai <csmthu@gmail.com >
2026-05-29 12:15:27 +08:00
40f91e6697
[Bugfix] [DSA] [Hisparse] Broadcast TP Rank 0 Topk Indexes to other TPs ( #24654 )
...
Co-authored-by: xz-keg <xuzou_keg@outlook.com >
Co-authored-by: xuzou <xu.zou@aminer.cn >
2026-05-28 21:14:46 -07:00
Cheng Wan
84698b21e7
rename unittest as unittests ( #26654 )
2026-05-28 21:14:06 -07:00
Dawid Majchrowski
3ea9607d1c
[diffusion] model: update to new model format ( #26492 )
2026-05-29 12:08:45 +08:00
Khoa Pham and Cursor
621a79728c
test: stabilize Gemma4 26B-A4B MTP GSM8K test with deterministic inference + tuned threshold ( #26653 )
...
Co-authored-by: Cursor <cursoragent@cursor.com >
2026-05-28 20:58:48 -07:00
Lianmin Zheng
dc4e7bc479
Fix TRTLLM MHA draft decode cache seqlens replay ( #26655 )
2026-05-28 20:58:16 -07:00
Xinyuan Tong
79c844527c
Upgrade xgrammar to 0.2.1 ( #25676 )
2026-05-29 11:40:07 +08:00
YC Yen-Ching Tseng
272066566f
[AMD] Pin compressed-tensors<0.16.0 for srt_hip (fixes ROCm 7.2 nightly build) ( #26591 )
2026-05-29 11:34:45 +08:00
McZyWu
b1173c8c14
[NPU] Enhance accuracy for model Step3_5 from 0 to 88% ( #24582 )
2026-05-29 11:29:30 +08:00
LucQueen and ZhengWG
36d0a6e08e
[EPD] Optimize the Mooncake backend ( #22587 )
...
Co-authored-by: ZhengWG <zwg0606@gmail.com >
2026-05-29 10:42:24 +08:00
Michael
569ee93357
[AMD] ci: switch CACHE_HOST to a fresh path to fix "No space left on device" ( #26642 )
2026-05-29 10:40:54 +08:00
monkeyLoveding
7619e77b7b
[NPU] chore: basic software upgrade ( #26466 )
2026-05-29 10:04:15 +08:00
Erik Wijmans
54b06f199c
[lora] Share MoE LoRA Info ( #24160 )
2026-05-29 11:01:47 +09:00
Cheng Wan and Claude Sonnet 4.6
e381312664
Revert "Fix FA DRAFT_EXTEND_V2 cache extent" ( #26628 )
...
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-05-28 18:45:33 -07:00
Rohit Kumar Singh
0f8104ef15
[XPU] Fix Device Assignment ( #26257 )
2026-05-29 09:38:11 +08:00
liuxianglong17
6258947039
NPU Nightly Pipeline Skip Test Case Adaptation and Recovery Testing ( #26353 )
2026-05-29 09:29:25 +08:00
McZyWu
1c2857b064
bugfix: --decrypted-draft-config-file not applied ( #25960 )
2026-05-29 09:15:05 +08:00
Kurkur
fffdfb6fcb
[Fix][NPU] Preserve existing packed_modules_mapping when merging model-level fused module mappings ( #25755 )
2026-05-29 09:11:36 +08:00
Qiaolin Yu