 DarkSharpnessandClaude Fable 5
|
8bb0d8d005
|
[JIT] Trait-driven per_token_group_quant: unify the quant kernel family (flat + masked) (#30924)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-22 08:46:52 +08:00 |
|
|
Liangsheng Yin
|
024639a372
|
[Perf] Stack dspark dense draft per-layer ctx KV projection into one GEMM (#31986)
|
2026-07-21 17:46:13 -07:00 |
|
|
Fardin Hoque
|
b54adced46
|
[Quant] Support NVFP4_AWQ checkpoints in ModelOpt FP4 path (#31825)
|
2026-07-22 08:46:10 +08:00 |
|
|
Muqi Li
|
a2c38175a4
|
fix(marlin_nvfp4): only apply routed_scaling_factor in moe_sum_reduce (#31762)
Signed-off-by: Muqi Li <muqi1029@gmail.com>
|
2026-07-22 08:45:42 +08:00 |
|
|
|
03342e7732
|
Delete sgl-kernel AOT router GEMM and fused A GEMM (#30280)
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
Co-authored-by: root <root@sgl-b300-inference.datacrunch.io>
|
2026-07-22 08:44:59 +08:00 |
|
|
Liangsheng Yin
|
8ae0eb83fc
|
[Perf] Fold dspark dense draft embedding into the draft graph via forward_embed (#31985)
|
2026-07-21 17:00:42 -07:00 |
|
|
Brayden Zhongandroot
|
2f4f2362fb
|
Delete sgl-kernel AOT bmm_fp8, use flashinfer.bmm_fp8 (#31202)
Co-authored-by: root <root@sgl-b300-inference.datacrunch.io>
|
2026-07-22 07:44:47 +08:00 |
|
|
Liangsheng Yin
|
08cb081ed0
|
[Perf] Skip page-table columns past kv length in DSA draft-extend metadata kernel (#31981)
|
2026-07-21 16:20:14 -07:00 |
|
|
Raghavendra Vedula
|
9057db9417
|
Gate Mamba slot-donation debug asserts behind SGLANG_MAMBA_DEBUG_ASSERTS (#31982)
|
2026-07-21 15:28:23 -07:00 |
|
|
JD
|
becf252e6c
|
AutoWeightLoader support Sglang native models 1: demo (#28671)
|
2026-07-21 14:32:13 -07:00 |
|
|
Brayden ZhongandBrayden Zhong
|
0eae9423d8
|
Change the FP8 per-tensor GEMM backend on SM120 to cuBLAS (#31961)
Co-authored-by: Brayden Zhong <brayden.zhong@radixark.ai>
|
2026-07-21 14:09:01 -07:00 |
|
|
Hanming Lu
|
d03c8cee80
|
Negotiate PrefillDelayer only after KV-budget admission checks (#31835)
|
2026-07-21 12:07:30 -07:00 |
|
|
Hanming Lu
|
927979e127
|
Fix pad-row top-k masking with custom_routing_function under DP attention (#31838)
|
2026-07-21 11:49:17 -07:00 |
|
|
Yanbin Jiang
|
57e5846b90
|
[LoRA] Guard TMA down path for LoRA hooks (#31608)
|
2026-07-21 09:47:17 -07:00 |
|
|
Zheng Wengangandsiyu
|
6f55de0468
|
[EPD] Make encoder register/unregister health-check robust (#31576)
Co-authored-by: siyu <liusy58@linux.alibaba.com>
|
2026-07-21 22:36:11 +08:00 |
|
|
Артем Савкин
|
8260ade61b
|
[Bugfix] Fix CUDA import on non-CUDA platforms (#31919)
|
2026-07-21 21:47:46 +08:00 |
|
|
Xiaoyu Zhang
|
075bd97952
|
[Benchmark] Remove obsolete auto-benchmark remnants (#31941)
|
2026-07-21 20:44:52 +08:00 |
|
|
Ke Bao
|
0a06cc5317
|
Fix extra_buffer_lazy guard bypass (#31942)
|
2026-07-21 20:41:35 +08:00 |
|
|
|
e4eea7ce2f
|
Optimize LongCat-Flash router GEMM with the HPC-Ops bf16xfp32 kernel (#30247)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Halcyon <56064364+VAthree@users.noreply.github.com>
|
2026-07-21 20:05:17 +08:00 |
|
|
qyb233
|
303896a475
|
[Bugfix] Place empty Qwen encoder-DP embeddings on the communication device (#31663)
|
2026-07-21 19:54:36 +08:00 |
|
|
YAMY
|
7c9257529f
|
[Mamba] Support speculative decoding with extra_buffer_lazy (#30437)
|
2026-07-21 19:38:03 +08:00 |
|
|
|
1a53f231d6
|
[HiCache]: Optimize hybrid/DSA L3 prefetch result sync and usable-prefix clamping (#31443)
Co-authored-by: AlejandroParedesLT <alejandroparedeslatorre@gmail.com>
Co-authored-by: Kevin Flansburg <kevin.flansburg@gmail.com>
Co-authored-by: Chao Shi <chao.shi@alibaba-inc.com>
|
2026-07-21 18:59:51 +08:00 |
|
|
|
df39a7b0b6
|
[CI][PD] Add NIXL disaggregation functional tests (#27894)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Shangming Cai <csmthu@gmail.com>
|
2026-07-21 18:17:06 +08:00 |
|
|
Ke Bao
|
2cf2e7377f
|
Fix dropped tool calls when a stream delta carries several (#31860)
|
2026-07-21 18:07:43 +08:00 |
|
|
Chao ShiandZhangheng
|
f369a820d4
|
[HiCache] Remove redundant parameters of build_xxx_stack and others (#31308)
Co-authored-by: Zhangheng <hzh0425@apache.org>
|
2026-07-21 17:54:06 +08:00 |
|
|
|
dcd9014f15
|
[AMD][MXFP4] Reland "Online MXFP4 quantization 2/N - FP8 to MXFP4 requantization on AMD GPUs" (#28291)
Co-authored-by: Bowen Bao <bowenbao@amd.com>
Co-authored-by: HAI <hixiao@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-07-21 02:50:23 -07:00 |
|
|
wenxuewuhd
|
c0ed009f5b
|
[NPU] Fix LLaDA2 MoE OOM after the FRACTAL_NZ cast, re-enabling the NZ speedup (#31772)
|
2026-07-21 16:09:34 +08:00 |
|
|
Lianmin Zheng
|
429f6b6d15
|
Turn on breakable prefill cuda graph for dp attention by default (#31682)
|
2026-07-21 00:03:43 -07:00 |
|
|
Yuhao Yang
|
37a830b667
|
[Feature] Add DWDP (Distributed Weight Data Parallelism) for MoE prefill (#29778)
|
2026-07-20 23:59:54 -07:00 |
|
|
JINO ROHITandgithub-actions[bot]
|
01f558d905
|
Sm120 scatter fallback (#31669)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
|
2026-07-20 23:58:27 -07:00 |
|
|
iridiumine
|
d6ef68881e
|
[NPU] Adapt MiMo-V2.5-W8A8 (#29131)
|
2026-07-21 09:16:48 +08:00 |
|
|
Rahul Vijayaraghavan
|
fa0ced195e
|
[XPU] Enable breakable prefill CUDA graph on XPU (#30273)
|
2026-07-21 09:09:40 +08:00 |
|
|
Zaili Wang
|
bfefdc52d7
|
[CPU] Fix mxfp4 padding size (#31334)
|
2026-07-21 09:03:24 +08:00 |
|
|
paulzhang-tm
|
d093c6a4bb
|
[FullCG] Preserve attention LSE through the custom-op boundary (#31050)
|
2026-07-21 09:01:40 +08:00 |
|
|
Yang Liu
|
9462c303a5
|
Fix stop boundaries for grammar-constrained speculative decoding (#31738)
|
2026-07-20 17:55:27 -07:00 |
|
|
Mick
|
4682ded472
|
vlm: parallelize multimodal preprocessing with customized worker num (#31438)
|
2026-07-21 08:44:58 +08:00 |
|
|
Lianmin ZhengandJason Park
|
e7e8aaa73c
|
Overlap grammar (constrained decoding) with speculative decode verify (#31488)
Co-authored-by: Jason Park <jasonjk@fb.com>
|
2026-07-20 17:36:05 -07:00 |
|
|
zijiexia
|
8905cbd42f
|
Fix MiniMax-M3 crash on ROCm by making its override fields resolvable (#31837)
|
2026-07-20 16:14:12 -07:00 |
|
|
Mohammad Miadh Angkad
|
a82ead53bd
|
Make Q contiguous before TRT-LLM MHA decode (#31667)
|
2026-07-20 15:21:00 -07:00 |
|
|
Liangsheng Yin
|
7fe9ad25ac
|
[Spec] Extract DFlash compact draft-cache rebuild helpers (#31677)
|
2026-07-20 15:07:55 -07:00 |
|
|
Kaixi
|
91b210f7b0
|
[GLM5][MoE] perf: Write FlashInfer TRT-LLM MoE output directly (#28416)
|
2026-07-20 13:45:23 -07:00 |
|
|
|
e856eae921
|
use sgl_kernel_npu rmsrope accelerate llada2 (#27127)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: ronnie_zheng <zl19940307@163.com>
|
2026-07-20 22:46:17 +03:00 |
|
|
Liangsheng Yin
|
ff6c755952
|
[Refactor] Unify logprob results into a single LogprobResult and rename chunk env vars (#31733)
|
2026-07-20 12:44:27 -07:00 |
|
|
Lianmin Zheng
|
54aaedd76d
|
Clean up prefill CUDA graph runner (#31654)
|
2026-07-20 12:14:21 -07:00 |
|
|
RockduandClaude Opus 4.8
|
4e8eb1457b
|
[Diffusion] msgpack raw-bytes transport (drop base64/JSON) (#31565)
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
|
2026-07-20 11:32:02 -07:00 |
|
|
Ke Bao
|
5ab3d90b81
|
Fix dropped Inkling reasoning at stream end (#31787)
|
2026-07-20 23:23:15 +08:00 |
|
|
Ke Bao
|
7fc545b649
|
Align reasoning_effort schema across chat, tokenize, and responses (#31784)
|
2026-07-20 23:22:43 +08:00 |
|
|
|
c41c573ce9
|
[GDN] Support ReplaySSM Ring Spec-Verify (#28695)
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
Co-authored-by: vincentzed <207368749+vincentzed@users.noreply.github.com>
|
2026-07-20 22:06:30 +08:00 |
|
|
heziiop
|
370f454e3d
|
[NPU] fix modelslim quant tensor name (#31456)
|
2026-07-20 20:32:57 +08:00 |
|
|
Mohammad Miadh Angkad
|
3d82dacd58
|
Bump CuTe DSL to 4.6.0 (#31714)
|
2026-07-20 02:11:59 -07:00 |
|