 Mick
|
643e1cc779
|
fix: fix prefill-aware SWA floor tracking (#29520)
|
2026-06-28 14:18:28 +08:00 |
|
|
Xinyuan Tong
|
ddc389cf09
|
[minimax-m3] Split 3/4: disagg K-only index-K transfer (#28714)
|
2026-06-28 13:54:42 +08:00 |
|
|
Lianmin Zheng
|
6eedc8f376
|
Fix EAGLE draft hidden dim extraction and centralize spec helpers (#29464)
|
2026-06-27 21:48:26 -07:00 |
|
|
Lianmin ZhengandYinghai Lu
|
5747ed3b19
|
Fix DP-attention SHM feature finalization race (#29543)
Co-authored-by: Yinghai Lu <yinghai@meta.com>
|
2026-06-27 21:36:58 -07:00 |
|
|
Mick
|
4a76699dfc
|
[diffusion] fix: fix --warmup silently downgrading server-based warmup to request mode (#29514)
|
2026-06-28 11:46:07 +08:00 |
|
|
Lianmin Zheng
|
e6cbc8f5fe
|
Fix SWA cache loc slicing for all attention backends (#29460)
|
2026-06-27 20:37:58 -07:00 |
|
|
Liangsheng Yin
|
4e6ce8e4ab
|
[Spec] Capture DFLASH draft greedy sampling inside the draft decode cuda graph (#29395)
|
2026-06-27 19:34:26 -07:00 |
|
|
Khoa PhamandCursor
|
da802ddcaf
|
(perf): Shard Kimi-K2.5 Eagle3 draft fc + symm-mem AG (#29223)
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-06-27 17:40:32 -07:00 |
|
|
|
073de15053
|
Fuse the DSA (V3.2, GLM-5.x) indexer Q/K paths into single kernels (#27705)
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
Co-authored-by: Kaixi <kaiximatteoc@nvidia.com>
|
2026-06-27 14:29:56 -07:00 |
|
|
Brayden ZhongandBrayden Zhong
|
e4253b39e2
|
Support JIT fused A GEMM (MLA down projection) and support GLM-5 hidden size, SM120 (#27397)
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
|
2026-06-27 13:32:06 -07:00 |
|
|
Xinyuan Tongandhzh0425
|
592f6c849b
|
[minimax-m3] Split 2/4: mem-cache / HiCache / sparse KV pool (#28713)
Co-authored-by: hzh0425 <hzh0425@apache.org>
|
2026-06-28 00:19:38 +08:00 |
|
|
Aditya KamatandMick
|
1589603114
|
model: support baidu unlimited-ocr (#29186)
Co-authored-by: Mick <mickjagger19@icloud.com>
|
2026-06-27 23:36:19 +08:00 |
|
|
|
b030b1a5f3
|
hisparse: support NIXL DRAM KV destinations for HiSparse (#27563)
Co-authored-by: Zhangheng <hzh0425@apache.org>
Co-authored-by: Shangming Cai <csmthu@gmail.com>
|
2026-06-27 22:32:29 +08:00 |
|
|
|
c1b5c7e499
|
Fix DeepSeek V4 PP HiCache SWA allocation and layer mapping (#29106)
Co-authored-by: hjzhang <zhanghjzzz@qq.com>
Co-authored-by: hzh0425 <hzh0425@apache.org>
|
2026-06-27 22:19:14 +08:00 |
|
|
jonah-bermanandXinyuan Tong
|
2f34dbe372
|
Add native Exa-backed web_search support (#29342)
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
|
2026-06-27 14:41:09 +01:00 |
|
|
Mick
|
3306233961
|
[diffusion] optimize: optimize LTX2.3 CFG path (#28624)
|
2026-06-27 19:23:14 +08:00 |
|
|
Mick
|
91f9e7372d
|
[diffusion] CI: refactor CI (#28762)
|
2026-06-27 19:22:27 +08:00 |
|
|
|
9214b9338f
|
[DSA] Enable draft-extend CUDA graph for DeepSeek Sparse Attention (#29413)
Co-authored-by: kpham-sgl <kpham-sgl@users.noreply.github.com>
Co-authored-by: Jackey Hua <107608053+zhendonghua@users.noreply.github.com>
|
2026-06-26 23:53:46 -07:00 |
|
|
Raiden MakotoandRaiden-Makoto
|
81d3c3ce77
|
[AMD] [GLM5] Guard cuda_runtime.h for ROCm in fused_metadata_copy (#29373)
Co-authored-by: Raiden-Makoto <Raiden-Makoto@users.noreply.github.com>
|
2026-06-26 23:29:19 -07:00 |
|
|
Xiaoyu Zhang
|
c36f166364
|
[skill] Remove outdated llm-serving-auto-benchmark skill (#29487)
|
2026-06-27 14:19:11 +08:00 |
|
|
Chengze Fan
|
43435a2f8e
|
[mori] Add a combine-kwargs hook and use_external_inp_buf plumbing (#29097)
|
2026-06-26 22:34:27 -07:00 |
|
|
Chengze Fan
|
19abebcc6a
|
[server_args] Make MoRI per-rank dispatch-token requirement overridable (#29096)
|
2026-06-26 22:25:36 -07:00 |
|
|
Xiaoyu ZhangandClaude Opus 4.8
|
495f13fa12
|
[KDA-Pilot] Add diffusion residual-gate CUDA fast path for LTX2 (#29361)
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
|
2026-06-27 12:59:41 +08:00 |
|
|
Lianmin Zheng
|
09ca4fc96b
|
Skip FlashInfer FP8 autotune for MXFP8 quantized models (#29462)
|
2026-06-26 18:15:08 -07:00 |
|
|
IvanShan177andClaude Opus 4.8
|
13b5bd962a
|
fix(spec): track current_token in ReasonerGrammarObject (#29102)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-06-26 16:43:35 -07:00 |
|
|
|
da0f4f6f92
|
[HiCache] remove large host mem constraint (#28614)
Co-authored-by: Teng Ma <stmatengss@gmail.com>
Co-authored-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
|
2026-06-26 16:20:48 -07:00 |
|
|
Lianmin Zheng
|
9c3227b689
|
Fix IPv6 wildcard bootstrap address resolution in disagg (#29459)
|
2026-06-26 16:05:36 -07:00 |
|
|
Po-Han Huang (NVIDIA)
|
72812db138
|
Avoid dynamic Q quantization in trtllm_mha (#29423)
|
2026-06-26 15:51:15 -07:00 |
|
|
Baizhou Zhang
|
73741f7074
|
Bypass legacy GLM DSA layer types validation (#29454)
|
2026-06-26 15:24:16 -07:00 |
|
|
|
267d165ad0
|
shm_broadcast: retry bind on EADDRINUSE (fix dp-attention port race) (#29455)
Co-authored-by: Xingyu Liu <38244988+charlotte12l@users.noreply.github.com>
Co-authored-by: xingyuliu <xingyuliu@fb.com>
|
2026-06-26 14:49:39 -07:00 |
|
|
Jimmy Shong
|
e745b3af22
|
[Fix] compressed-tensors block FP8: requantize weight scales to UE8M0 for DeepGEMM on Blackwell (#28662)
|
2026-06-26 21:41:18 +00:00 |
|
|
Cheng Wan
|
7b02eab7a6
|
Revert "[DeepSeek V3] Run routed experts on main stream in dual-stream MoE" (#29452)
|
2026-06-26 13:59:36 -07:00 |
|
|
Jackey HuaandClaude Opus 4.8
|
ee77a7d330
|
[Fix] DSA: size cudagraph page_table to req_to_token width (#29379)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-06-26 12:17:34 -07:00 |
|
|
Rain JiangandLianmin Zheng
|
be1930133a
|
Convert IPC dataclasses to msgspec.Struct with opt-in msgpack transport (#28688)
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
|
2026-06-26 12:04:03 -07:00 |
|
|
|
714011a40f
|
[JIT Kernel] Migrate dsv3_router_gemm from AOT sgl-kernel to JIT kernel (#21531)
Co-authored-by: Guohao Shao <shao.gh.98@gmail.com>
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
|
2026-06-26 11:52:18 -07:00 |
|
|
Xiaoyu Zhang
|
8524678889
|
Fix MiniMax MSA fallback when fmha plan is unavailable (#29250)
|
2026-06-26 23:14:31 +08:00 |
|
|
Xiaoyu Zhang
|
18b0e5757e
|
[Diffusion] Fuse LTX2 Ada values (#29390)
|
2026-06-26 23:13:15 +08:00 |
|
|
Aleksi Vesanto
|
b91348071e
|
[diffusion] optimize: shard qwen text embed in sp (#29147)
|
2026-06-26 21:44:45 +08:00 |
|
|
syy-hw
|
f5708c3f91
|
[NPU] Fix mllama cross-attention crash in ascend extend SDPA (#29374)
|
2026-06-26 17:13:17 +08:00 |
|
|
Yan Ru Pei
|
c0d4d1897c
|
fix: batch BlockRemoved events per radix node (#29265)
|
2026-06-26 16:13:40 +08:00 |
|
|
|
999199f9ff
|
[DeepSeek V3] Run routed experts on main stream in dual-stream MoE (#29142)
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
2026-06-26 00:48:59 -07:00 |
|
|
|
aeb4e98108
|
[diffusion] model: support JoyEcho multi-shot A/V generation support (#27420)
Co-authored-by: niehen6174 <niehen6174@users.noreply.github.com>
Co-authored-by: 1639206518@qq.com <niehen6174>
|
2026-06-26 15:46:31 +08:00 |
|
|
Xiaoyu ZhangandClaude Opus 4.8
|
5996b54bd3
|
[KDA-Pilot] Add diffusion causal Conv3D cat-pad CUDA fast path for Cosmos3 (#29281)
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
|
2026-06-26 15:06:49 +08:00 |
|
|
Yuan Luoandluoyuan.luo
|
a10a24e9a7
|
[GDN][KDA] ReplaySSM buffered output-only decode for Linear Attention (#28451)
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
|
2026-06-26 14:17:02 +08:00 |
|
|
Polisetty V R K Jyothendra VarmaandMa Mingfei
|
dc113e8804
|
[Intel GPU] DeepSeek V4 3/N: Support hc_split_sinkhorn on XPU using sgl_kernel (#27783)
Signed-off-by: P V R K Jyothendra Varma <polisetty.v.r.k.jyothendra.varma@intel.com>
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
|
2026-06-26 13:57:13 +08:00 |
|
|
Khoa PhamandCursor
|
eeee3abbbf
|
[CI] Fix false spec accept length failure after profiling phase (#29329)
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-06-25 22:19:30 -07:00 |
|
|
ziang663
|
ff89e0fe9a
|
Fix KV event publisher bind conflict under PP (#29044)
|
2026-06-26 12:50:49 +08:00 |
|
|
ziang663
|
8fd6e9e017
|
Fix fixed-size HiCache capacity under PP (#29258)
|
2026-06-26 12:49:23 +08:00 |
|
|
Liangsheng Yin
|
b6ebdcc92e
|
[test] Split perf table out of fwd occupancy kit report (#29348)
|
2026-06-25 20:23:42 -07:00 |
|
|
|
cfc0a0e0e0
|
Add Intel Quantization Support in SGLang (#18139)
Signed-off-by: Mengni Wang <mengni.wang@intel.com>
Signed-off-by: WeiweiZhang1 <weiwei1.zhang@intel.com>
Co-authored-by: Peng Zhang <aniz1905@gmail.com>
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
Co-authored-by: Weiwei <weiwei1.zhang@intel.com>
|
2026-06-26 09:54:35 +08:00 |
|