 Xiaoyu ZhangandBBuf
|
d6e0a8cbf4
|
[diffusion] add Helios per-token gated-residual fusion (quality-gated) (#38042)
Co-authored-by: BBuf <bbuf@users.noreply.github.com>
|
2026-09-05 10:29:09 +08:00 |
|
|
Niko MaandZhangheng
|
f1f2380d2b
|
[Unified Cache][6/N]: Add UMBP external linker (#37578)
Co-authored-by: Zhangheng <hzh0425@apache.org>
|
2026-09-05 09:21:43 +08:00 |
|
|
Xiaoyu ZhangandBBuf
|
bc727bc4ee
|
[FP8] SM120: route FP8 linear to per-tensor (cudnn/nvjet) instead of channelwise cutlass (#38006)
Co-authored-by: BBuf <bbuf@example.com>
|
2026-09-05 09:07:13 +08:00 |
|
|
|
55bf3380e0
|
Support Hy4-preview (#36805)
Co-authored-by: BBuf <1182563586@qq.com>
Co-authored-by: alphabetc1 <2508695655@qq.com>
|
2026-09-04 18:03:49 -07:00 |
|
|
Xiaoyu Zhang
|
85da5457de
|
[diffusion] auto-keep video DiT resident on high-memory GPUs (#38001)
|
2026-09-05 08:54:09 +08:00 |
|
|
|
3c2724c48d
|
[AMD] Optimize Kimi-K3 Triton MLA prefill on gfx950 (#35770)
Co-authored-by: clintg6 <7388379+clintg6@users.noreply.github.com>
Co-authored-by: Thomas Wang <thomawan@amd.com>
Co-authored-by: HAI <hixiao@gmail.com>
Co-authored-by: kk <43161300+kkHuang-amd@users.noreply.github.com>
|
2026-09-04 17:44:30 -07:00 |
|
|
Alex Nails
|
a44bb397a9
|
[Perf] Vectorize alloc_extend_naive to remove the per-request Python loop (#37938)
|
2026-09-04 17:26:25 -07:00 |
|
|
Lianmin Zheng
|
613d87becd
|
[Memory] Reuse output storage across full prefill CUDA graphs (#38038)
|
2026-09-04 17:23:31 -07:00 |
|
|
YAMY
|
65f7957142
|
fix: gather CP-sharded tokens before TP-sharded dense MLP under prefill CP (#38078)
|
2026-09-04 17:14:31 -07:00 |
|
|
Amy Chang
|
8a98f11078
|
[feature] Add response-level input/output token ids to chat completions via SglExt (#34488)
|
2026-09-04 16:45:13 -07:00 |
|
|
PengYuanandMick Qian
|
9c254df8cd
|
[diffusion] fix: preserve mapped courier tensor lifetime (#37965)
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
|
2026-09-05 07:41:47 +08:00 |
|
|
YAMY
|
db89f639ef
|
[GDN] Amortize ReplaySSM checkpoint materialization (#35544)
|
2026-09-04 15:13:20 -07:00 |
|
|
Hanming Lu
|
e3eeabbbfa
|
[Profiler] Add SGLANG_PROFILE_BY_STAGE_DECODE_MIN_BS to defer the decode-stage capture (#38067)
|
2026-09-04 15:12:55 -07:00 |
|
|
cctry
|
0eff0f7460
|
Add num_prealloc_ready_tokens to decode load snapshot (#38065)
|
2026-09-04 15:05:57 -07:00 |
|
|
Yongji WuandLianmin Zheng
|
fbf8f1dbf6
|
[Fix] Coordinate FullCG prefix variants across DP ranks (#37888)
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
|
2026-09-04 11:29:30 -07:00 |
|
|
Jialin OuyangandPranjal Shankhdhar
|
010dc955be
|
[Metrics] Export scheduler stage wall time (#37636)
Co-authored-by: Pranjal Shankhdhar <pranjal.ssh@gmail.com>
|
2026-09-04 10:45:53 -07:00 |
|
|
YAMY
|
07199fa220
|
[Performance] Optimize Qwen3.5 GDN prefill projection layouts (#36267)
|
2026-09-04 10:32:44 -07:00 |
|
|
Shuwen WangandClaude Fable 5.1
|
5cd2a7661d
|
fix: reformat cosmos3_edge.py to satisfy ruff-format (#38023)
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
|
2026-09-04 23:39:36 +08:00 |
|
|
huangtingweiandZhiqiang Xie
|
0d0e2f92be
|
[HiCache] Buffer mode support sidecar pool (#37424)
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
|
2026-09-04 23:24:18 +08:00 |
|
|
|
8b1d8c1703
|
[Metrics] Add rolling scheduler utilization counters (#37461)
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
Co-authored-by: pranjalssh <pranjalssh@fb.com>
|
2026-09-04 08:06:17 -07:00 |
|
|
|
4349538c02
|
[model] add cosmos3 reasoner to llm only inference (#33572)
Signed-off-by: joeltg <joel@reflection.ai>
Signed-off-by: Joe Rowell <joe@poolside.ai>
Co-authored-by: Dawid Majchrowski <dmajchrowski@nvidia.com>
Co-authored-by: Kedi Wu <kediw@nvidia.com>
Co-authored-by: Kedi Wu <31940276+kediwu0331@users.noreply.github.com>
Co-authored-by: Joel Gustafson <joelgustafson@protonmail.com>
|
2026-09-04 22:11:58 +08:00 |
|
|
Shuwen Wang
|
19b46863f3
|
fix: align write-through pending across tree cores (#37278)
|
2026-09-04 22:08:25 +08:00 |
|
|
Mick
|
88021b0734
|
[diffusion] chore: make nightly performance measurements robust (#37915)
|
2026-09-04 22:03:25 +08:00 |
|
|
Lianmin Zheng
|
978cc228ca
|
[Rust] Bound multimodal media ingress (#37967)
|
2026-09-04 05:22:44 -07:00 |
|
|
Shuwen WangandClaude Opus 5
|
e4adf63275
|
[Fix] Vacuous marker writes in the cache tests, and an undebited Mamba admission slot (#36415)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-09-04 19:43:17 +08:00 |
|
|
Kevin MiandClaude Fable 5.1
|
3b678549c3
|
[diffusion] chore: warm up minimax-h3 at the served clip shape (#37945)
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
|
2026-09-04 19:18:02 +08:00 |
|
|
Xiaoyu Zhang
|
f3b2725609
|
sm120 32GB mem-tier: raise decode cuda-graph max_bs 24->48 + chunked_prefill 2k->4k (#37898)
|
2026-09-04 18:47:26 +08:00 |
|
|
|
12735c2d76
|
[mm] refactor mm code for rust tokenizer manager (#34660)
Co-authored-by: Rain Jiang <rain-jiang@outlook.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-09-04 03:03:25 -07:00 |
|
|
CSWYF3634076androot
|
b42569a0f1
|
[Quant][ue8m0 fix] group requant_weight_ue8m0 reduce reserved gpu memory (#31755)
Co-authored-by: root <root@johor-edge-gpu-a17-13.bec-host.baidu.com>
|
2026-09-04 10:03:21 +00:00 |
|
|
Lianmin ZhengandShiyan Deng
|
d7f235daca
|
[Memory] Retire graph borrow pool before updating static runs (#37966)
Co-authored-by: Shiyan Deng <dsy842974287@meta.com>
|
2026-09-04 02:59:52 -07:00 |
|
|
|
44c786679f
|
[sp] Make attention-TP sequence sharding a per-forward batch property (#37546)
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
|
2026-09-04 02:11:03 -07:00 |
|
|
|
67248e04b4
|
[mem_cache] Route hybrid SWA full-side kv-row frees through free_segment (#37876)
Co-authored-by: weireweire <20922698+weireweire@users.noreply.github.com>
Co-authored-by: Sam Shleifer <sshleifer@gmail.com>
|
2026-09-04 01:48:33 -07:00 |
|
|
karverma-amdandwunhuang
|
dae126d510
|
[AMD][DSv4] Fuse inverse-RoPE into the fp8 wo_a quant (stacked on #37423) (#37658)
Co-authored-by: wunhuang <wunhuang@amd.com>
|
2026-09-04 00:51:29 -07:00 |
|
|
Ke Baoandadityakamat24
|
0b57847ebf
|
Fix mamba radix cache ssm state indexing (#37836)
Co-authored-by: adityakamat24 <adityakamat007@gmail.com>
|
2026-09-04 15:46:33 +08:00 |
|
|
Xiaoyu Zhang
|
01e66a62db
|
[Diffusion] Improve BCG warmup frame-count diagnostics for video models (#37890)
|
2026-09-04 15:05:24 +08:00 |
|
|
AMD-yanfeiwangandkk
|
7f89cc5286
|
[AMD] Skip unused TOPK v2 plan kernel on ROCm (#37580)
Co-authored-by: kk <43161300+kkHuang-amd@users.noreply.github.com>
|
2026-09-04 00:00:38 -07:00 |
|
|
|
1bda9694b7
|
[AMD][DSv4] Switch output projection gemm (oproj_a) to fp8 (#37423)
Signed-off-by: Hemanth Acharya <heachary@amd.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: kk <43161300+kkHuang-amd@users.noreply.github.com>
|
2026-09-03 23:56:07 -07:00 |
|
|
Polisetty V R K Jyothendra Varma
|
b168f905c8
|
[Intel GPU] Align XPU toml file for rust support (#31031)
Signed-off-by: P V R K Jyothendra Varma <polisetty.v.r.k.jyothendra.varma@intel.com>
|
2026-09-04 14:48:30 +08:00 |
|
|
Hemanth Acharya
|
31ebd8f437
|
[AMD][DSv4] Fuse the DSv4 FP4 indexer prefill-schedule preamble into one kernel (#37764)
|
2026-09-03 23:44:49 -07:00 |
|
|
Xiaoyu Zhang
|
54c2c99feb
|
[Diffusion] Fuse LingBot per-token gated residual and RMSNorm modulate (#37910)
|
2026-09-04 14:35:13 +08:00 |
|
|
Yu-Yun ChangandHAI
|
cb32dbc9e0
|
[AMD] [Kimi-K3] Fuse the KDA input projection into a single GEMM on ROCm (#35176)
Co-authored-by: HAI <hixiao@gmail.com>
|
2026-09-03 23:30:08 -07:00 |
|
|
|
72078cd7f5
|
[XPU] Support GPT-OSS MXFP4 checkpoints on Intel XPU (#35751)
Co-authored-by: Meng, Hengyu <hengyu.meng@intel.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-09-04 14:20:28 +08:00 |
|
|
Po-Han Huang (NVIDIA)andkpham-sgl
|
d122ca99b2
|
[Bugfix] Fix Llama 4 FA3 local attention with paged KV cache (#32902)
Co-authored-by: kpham-sgl <khoa.pham@radixark.ai>
|
2026-09-03 23:15:23 -07:00 |
|
|
mqhc2020andBingxu Chen
|
4e756ecc4a
|
[AMD] CI: fix Lean decode crash on the EAGLE path (#37119)
Co-authored-by: Bingxu Chen <bingxche@amd.com>
|
2026-09-03 23:04:21 -07:00 |
|
|
AMD-yanfeiwangandkk
|
7825e5ffca
|
[AMD] Fix DSV4 unified attention sink TP slice (#35092)
Co-authored-by: kk <43161300+kkHuang-amd@users.noreply.github.com>
|
2026-09-03 22:59:53 -07:00 |
|
|
Alex NailsandClaude Opus 5
|
ebae8ee21e
|
[Fix] Register triton.runtime.cache.triton_key in the MPS stub so torch.compile keeps working (#37937)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-09-03 22:56:14 -07:00 |
|
|
Xiaoyu Zhang
|
06b8749803
|
[Diffusion][Docs] Add single-GPU large-VRAM performance notes (B300) (#37891)
|
2026-09-04 13:33:28 +08:00 |
|
|
Mick
|
ed67b73081
|
[diffusion] UX: reduce hot-path server log noise (#37804)
|
2026-09-04 13:31:00 +08:00 |
|
|
Mohammad Miadh AngkadandMohammad Angkad
|
ca7b8efd87
|
[CI] Fix handle_platform_cp_compatibility reading legacy CP flags off the record (#37930)
Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
|
2026-09-03 22:07:04 -07:00 |
|
|
|
f478b2bb2d
|
Fix: abort handling for dispatched requests after client disconnect (#35255)
Signed-off-by: Shijin Zhang <75300765+Dovis01@users.noreply.github.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: cctry <cctry@fb.com>
|
2026-09-03 21:51:57 -07:00 |
|