 Mick
|
a18106bbc3
|
fix(vlm): make EPD cache publication transactional (#36949)
|
2026-09-05 20:33:23 +08:00 |
|
|
|
bd16c22a04
|
[diffusion] fuse LingBot MoE group-limited top-k index selection (#38044)
Co-authored-by: BBuf <bbuf@users.noreply.github.com>
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
|
2026-09-05 18:12:30 +08:00 |
|
|
DayuxiaoshuiandXiaoyu Zhang
|
50c1bf0db0
|
[Diffusion] Port the Wan VAE decoder fast paths to the Qwen-Image VAE (#38020)
Co-authored-by: Xiaoyu Zhang <1182563586@qq.com>
|
2026-09-05 18:02:33 +08:00 |
|
|
hhhh1252023
|
0948e6ebed
|
[CI] Remove metrics artifact mechanism from nightly NPU workflows (#35489)
|
2026-09-05 17:16:52 +08:00 |
|
|
Xiaoyu ZhangandBBuf
|
d49180019b
|
fix(moe): cast filtered-activation expert_ids to int32 for torch.compile (#38085)
Co-authored-by: BBuf <bbuf@users.noreply.github.com>
|
2026-09-05 17:13:07 +08:00 |
|
|
Xiaoyu Zhang
|
a74470e904
|
fix(mamba): unify causal_conv1d col* dtype to x (MiniCPM-V-4.6 GDN prefill bf16/fp16 mismatch) (#38039)
|
2026-09-05 17:08:20 +08:00 |
|
|
jacky.cheng
|
0bdc15d20f
|
[AMD] Fix ROCm VAE Conv2D fast path breaking spatial-parallel decode (#34424)
|
2026-09-05 01:00:25 -07:00 |
|
|
Xiaoyu Zhang
|
da76fa073f
|
[diffusion] fix: fix host-resident vocab tables loaded on GPU (#38012)
|
2026-09-05 14:03:21 +08:00 |
|
|
Mick
|
0ea8378085
|
[diffusion] feat: support request-scoped skip-softmax attention (#37959)
|
2026-09-05 13:50:17 +08:00 |
|
|
Shuwen WangandClaude Opus 5
|
4b44a1cde2
|
[Refactor] Let eviction policies take construction parameters (#37795)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-09-05 13:48:30 +08:00 |
|
|
Xinyuan Tong
|
32a1d55431
|
fix(modelopt_fp4): skip NVFP4 swiglu-fusion interleave for shared experts with swiglu_limit (#37378)
|
2026-09-04 22:42:29 -07:00 |
|
|
Ke Bao
|
ae3205ba28
|
Fail fast on undersized swa pool (#37610)
|
2026-09-05 13:40:37 +08:00 |
|
|
Yash AkhauriandXiaoyu Zhang
|
756d0e0a85
|
[Model] Add K2 Horizon FP8 checkpoint support (#38033)
Co-authored-by: Xiaoyu Zhang <1182563586@qq.com>
|
2026-09-05 13:18:26 +08:00 |
|
|
|
e980c1a2f1
|
fix(glm4v): disambiguate mixed image video offsets (#37971)
Co-authored-by: duxin <xinheng.dx@alibaba-inc.com>
Co-authored-by: Xiaoyu Zhang <1182563586@qq.com>
|
2026-09-05 13:16:16 +08:00 |
|
|
Liangsheng Yin
|
0454c074b4
|
[mem_cache] Clean up unified allocator leftovers (#38103)
|
2026-09-04 22:02:50 -07:00 |
|
|
|
3a770da756
|
[Unified Tree] Support Branching-Point Caching for the SWA Component (#34565)
Co-authored-by: alphabetc1 <2508695655@qq.com>
Co-authored-by: Shuwen Wang <47200617+alphabetc1@users.noreply.github.com>
|
2026-09-05 12:29:16 +08:00 |
|
|
Po-Han Huang (NVIDIA)
|
991368d880
|
Fix Muse Glimmer ModelOpt mixed weight mapping (#37510)
|
2026-09-04 20:53:55 -07:00 |
|
|
|
92a4d8b5ee
|
Clean logging under --weight-loader-prefetch-checkpoints (#33930)
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
Co-authored-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
|
2026-09-04 20:05:53 -07:00 |
|
|
Liangsheng Yin
|
0645398a32
|
[mem_cache] Move the unified-memory allocators into allocator/ and split the composites out (#38072)
|
2026-09-04 19:53:15 -07:00 |
|
|
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 |
|