 Baizhou ZhangandRyan Stewart
|
41e7612dee
|
[Model] Support Nemotron 3.5 Lightning speculative decoding (#36186)
Co-authored-by: Ryan Stewart <rystewart@nvidia.com>
|
2026-08-25 16:43:58 -07:00 |
|
|
Baizhou Zhang
|
2d88c79b3e
|
[CI] Add Kimi-K3 MMMU-Pro accuracy coverage (#36284)
|
2026-08-25 16:33:46 -07:00 |
|
|
cctry
|
aa718f7343
|
Refactor HiCache host pool management (#36232)
|
2026-08-25 16:31:57 -07:00 |
|
|
|
0c42a44cd7
|
Add Spark3 Model (#35963)
Co-authored-by: Yaowj <yaowj@MacBook-Air.local>
Co-authored-by: ybyang <10629930+whybeyoung@users.noreply.github.com>
|
2026-08-25 16:24:00 -07:00 |
|
|
Leon Gao
|
f7a56494b1
|
Fix SWA ownership across grouped frees (#36381)
|
2026-08-25 14:57:30 -07:00 |
|
|
Junpan Wu
|
4b4bf3d2a5
|
[Deepseek-V4] Enable shared-experts fusion on the flashinfer_mxfp4 (trtllm-gen) MoE path (#35505)
Signed-off-by: Shiki Wu <shikiw@nvidia.com>
|
2026-08-25 14:55:25 -07:00 |
|
|
Shangming Cai
|
edff717ef0
|
fix(disagg): snapshot affected rooms before iterating outside the lock (#36351)
|
2026-08-26 03:31:10 +08:00 |
|
|
Kevin FlansburgandShangming Cai
|
7ddf92d5f4
|
fix(disagg): refresh stale prefill bootstrap metadata (#36029)
Co-authored-by: Shangming Cai <csmthu@gmail.com>
|
2026-08-26 03:29:20 +08:00 |
|
|
YAMY
|
e9c9df6a52
|
[Performance] Tune FlashInfer EXTEND for DP prefill (#36219)
|
2026-08-25 08:29:57 -07:00 |
|
|
elvischenv
|
46d9427b91
|
Fix MXFP8 MoE weight sizing for non-gated models (#36097)
|
2026-08-25 22:09:09 +08:00 |
|
|
Benjamin Truong
|
a1f9508dd4
|
[Bugfix] Fix int32 destination offset overflow in CUTLASS MoE pre-reorder (#35188)
|
2026-08-25 20:56:42 +08:00 |
|
|
|
829138a31e
|
[HiCache] Fix PP inconsistency with HiCache L3 (#22607) (#27010)
Co-authored-by: ybyang <ybyang7@iflytek.com>
Co-authored-by: hzh0425 <hzh0425@apache.org>
Co-authored-by: shangmingc <csmthu@gmail.com>
Co-authored-by: 晟海 <huangtingwei.htw@antgroup.com>
|
2026-08-25 20:49:57 +08:00 |
|
|
Cheng Wan
|
443527af0c
|
config: the model-config cache keys on the path the record carried (#36300)
|
2026-08-25 03:18:28 -07:00 |
|
|
jacky.cheng
|
6a81038317
|
[AMD] Drop redundant FP8 bpreshuffle scale transpose via fused AR kernel (#33021)
|
2026-08-25 02:49:57 -07:00 |
|
|
jiaryang
|
3bc1c580c6
|
[AMD] Enable draft_extend CUDA graph for HIP DSA backend (#35672)
|
2026-08-25 02:18:08 -07:00 |
|
|
|
8f096b853a
|
[diffusion] fix: crop GLM-Image output to requested size (#33859)
Co-authored-by: AuFlow <AuFlow@users.noreply.github.com>
Co-authored-by: ronnie_zheng <zl19940307@163.com>
|
2026-08-25 11:50:47 +03:00 |
|
|
Xinyi Song
|
2e3934f4cb
|
[AMD] Enable Mori-EP on kimi-k3 (#35630)
|
2026-08-25 01:48:09 -07:00 |
|
|
Mick
|
191244b3f6
|
[diffusion] feat: support loading Comfy NVFP4-AWQ text encoders (#36046)
|
2026-08-25 15:43:30 +08:00 |
|
|
Lianmin Zhengandyangliu991
|
bf1e03f712
|
[MegaMoE] Respect padded MXFP8 scale row strides in pre-dispatch (#36237)
Co-authored-by: yangliu991 <yangliu991@fb.com>
|
2026-08-25 00:27:33 -07:00 |
|
|
|
e2b50930b9
|
[NPU] DeepSeek-V4 adapt sgl-kernel-npu ops (compressor/sparse-attn/sparse-attn-metadata) (#35676)
Co-authored-by: vstone-w <374330057@qq.com>
Co-authored-by: unclezhou486 <154310456@qq.com>
Co-authored-by: 摆渡人 <2044145178@qq.com>
|
2026-08-25 15:13:12 +08:00 |
|
|
Артем Савкинandronnie_zheng
|
61b67316d8
|
[NPU] [Diffusion] Support MiniMax H3 on Ascend NPU's (#33569)
Co-authored-by: ronnie_zheng <zl19940307@163.com>
|
2026-08-25 09:44:14 +03:00 |
|
|
qinsir5522
|
f2ef826f0c
|
[NPU]Fix run_lora_a_embedding out-of-vocab token produces wrong embedding. (#32031)
|
2026-08-25 14:09:25 +08:00 |
|
|
Eric ZhangandNikita Shulga
|
7769ff8f1e
|
[DeepGEMM] Deduplicate JIT precompile across local ranks (#36231)
Co-authored-by: Nikita Shulga <nikita@thinkingmachines.ai>
|
2026-08-24 22:58:03 -07:00 |
|
|
|
2d6c12e2fd
|
[AMD] Don't request the unused softmax LSE in the AITER diffusion backend (#32926)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: YC Yen-Ching Tseng <yctseng@amd.com>
|
2026-08-24 22:27:42 -07:00 |
|
|
Wang, FangYuan
|
01db8a7829
|
[BugFix][Qwen3.8] Support Qwen3.8-MXFP4 DCP by registing Qwen3_5 text-only archs in mamba radix cache whitelists (#35297)
|
2026-08-24 22:13:59 -07:00 |
|
|
|
284ed9d1d3
|
[diffusion] feat: support LongCat-Image-Edit and LongCat-Image-Edit-Turbo (#35829)
Co-authored-by: 登辉 <yangdenghui.ydh@alibaba-inc.com>
Co-authored-by: Xiaoyu Zhang <1182563586@qq.com>
|
2026-08-25 12:42:08 +08:00 |
|
|
Mick
|
67853c5804
|
[diffusion] feat: dispatch fp8 companions in mixed NVFP4 checkpoints (#36066)
|
2026-08-25 11:26:37 +08:00 |
|
|
Cui Lily
|
1fa32d50e1
|
[XPU] Use SYCL kernels for DeepSeek V4 MHC on XPU (#32166)
Signed-off-by: Cui, Lily <lily.cui@intel.com>
|
2026-08-25 10:27:30 +08:00 |
|
|
Mick
|
f8f9226cd2
|
[diffusion] feat: support component-scoped quantization overrides (#36035)
|
2026-08-25 09:20:47 +08:00 |
|
|
Mick
|
ddea7b9156
|
[diffusion] feat: support mixed Comfy NVFP4 and INT8 layers (#36061)
|
2026-08-25 09:19:47 +08:00 |
|
|
pllimax
|
d2d8ecea77
|
[npu] Combine NPU test fixes from #35472 and #34516 (#36180)
|
2026-08-25 09:00:40 +08:00 |
|
|
eeecho
|
91e7e84ee5
|
[SM120] flash_mla: allocate the page-split buffer outside inference mode (#35116)
|
2026-08-24 17:42:23 -07:00 |
|
|
huangtingwei
|
0f7ba3d115
|
[HiSparse] Support hisparse multi-step swap io kernel (#32162)
|
2026-08-24 17:29:44 -07:00 |
|
|
|
effe0d14d2
|
[Fix] Keep the MiniCPM-SALA config reads visible to the resolution ratchets (#36178)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: Alex Nails <alex.nails@radixark.ai>
|
2026-08-24 16:05:09 -07:00 |
|
|
BingjiaWang
|
3c481b9421
|
[Benchmark] Add optional steady-state window for serving metrics (#30918)
|
2026-08-24 14:49:20 -07:00 |
|
|
AMD-yanfeiwang
|
24bce93c93
|
[AMD][MORI] Deduplicate CP-replicated state transfers (#36025)
|
2026-08-24 14:43:52 -07:00 |
|
|
jacky.cheng
|
0d5b5ae620
|
[AMD] Fix Qwen3.5 MTP dropping fused shared-expert weights (#35719)
|
2026-08-24 13:18:42 -07:00 |
|
|
jacky.cheng
|
0665740953
|
[AMD][Fix] Route MoRI through the Qwen MoE all-to-all path (#32039)
|
2026-08-24 13:04:08 -07:00 |
|
|
Ke Bao
|
d10a656ad8
|
Cleanup duplicate mamba backup helper (#36203)
|
2026-08-25 00:52:37 +08:00 |
|
|
Ke Bao
|
586211bc46
|
Add PD test for inkling with mxfp8 KV (#35840)
|
2026-08-25 00:12:05 +08:00 |
|
|
Ke Bao
|
54ec2c4699
|
Fix recurrent state loss on decode retraction (#35957)
|
2026-08-25 00:11:05 +08:00 |
|
|
Mick
|
30f9ed09d1
|
[diffusion] feat: support loading minimax h3 gguf text encoders (#36055)
|
2026-08-24 23:00:49 +08:00 |
|
|
Mick
|
9b0007ed19
|
[diffusion] feat: support loading comfy nvfp4 minimax h3 checkpoints (#36044)
|
2026-08-24 22:57:02 +08:00 |
|
|
Mick
|
76d1401881
|
[diffusion] feat: support mixed w4a4 and int8 checkpoints (#36040)
|
2026-08-24 20:35:11 +08:00 |
|
|
fzyzcjy
|
e586a6f2c5
|
Report the whole server's world size in the scheduler's internal state (#35929)
|
2026-08-24 20:21:45 +08:00 |
|
|
fzyzcjy
|
6dd79576cd
|
Expose the declared sglang env vars of a scheduler in its internal state (#35928)
|
2026-08-24 20:20:29 +08:00 |
|
|
fzyzcjy
|
c56cee0f80
|
Support gated launch to defer startup memory allocation (#35927)
|
2026-08-24 20:19:45 +08:00 |
|
|
fzyzcjy
|
3b24d8981b
|
Report per-token weight-version spans in generation meta info (#35926)
|
2026-08-24 20:18:52 +08:00 |
|
|
fzyzcjy
|
981dfa2b83
|
Make the scheduler track the published weight version (#35925)
|
2026-08-24 20:17:50 +08:00 |
|
|
fzyzcjy
|
02a3dca738
|
Extract _make_abort_req from the scheduler's abort paths (#35924)
|
2026-08-24 20:16:38 +08:00 |
|