 Nan Jiang
|
8600457731
|
[Spec] Propagate state capture outputs in DFlash (#34026)
|
2026-08-07 14:42:30 -07:00 |
|
|
YAMY
|
9e3f6b746b
|
fix(mamba): widen causal_conv1d token offsets to int64 (#33665)
|
2026-08-07 14:31:48 -07:00 |
|
|
Brayden ZhongandBrayden Zhong
|
b3ee679467
|
[MXFP8] Use FlashInfer CUTLASS for dense GEMM on SM120, delete Triton path (#33208)
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
|
2026-08-07 14:30:43 -07:00 |
|
|
Dmitrii Sergeev
|
699fcdc936
|
Fix _pa_swa_prefill_lens off-by-one in FlashAttentionBackend (#33379)
|
2026-08-07 14:06:48 -07:00 |
|
|
Sam ShleiferandClaude Fable 5
|
62a28197c0
|
Autotune flashinfer extend buckets at warmup (#32556)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-08-07 14:06:05 -07:00 |
|
|
Zhangheng
|
1480687cff
|
[CP]: Support CP V2 Strategy for dsv4 (#33532)
|
2026-08-07 14:03:27 -07:00 |
|
|
Sam Shleifer
|
8e7d361def
|
[perf] Compute input logprobs without materializing the full-vocab log-softmax (#31958)
|
2026-08-07 14:01:08 -07:00 |
|
|
Hanming LuandLianmin Zheng
|
b53a39c5e4
|
Limit prefill delayer debug logs to rank zero (#34020)
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
|
2026-08-07 13:41:19 -07:00 |
|
|
Oguz UlgenandYinghai Lu
|
7f6b4cb94b
|
Add CUDA VMM multimodal feature transport (#33899)
Co-authored-by: Yinghai Lu <yinghai@meta.com>
|
2026-08-07 13:39:54 -07:00 |
|
|
|
3c51e29deb
|
Responses support (#32689)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Harmya Bhatt <harmyacs@gmail.com>
Co-authored-by: harmya <harmya@modal.com>
Co-authored-by: Xinyuan <xinyuan@radixark.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
|
2026-08-07 13:21:46 -07:00 |
|
|
Xiaoyu ZhangandClaude Fable 5
|
6c7498113f
|
[diffusion] Enable breakable CUDA graph for SANA (H200 1024px e2e -26%, bit-exact) (#33989)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-08-07 23:54:39 +08:00 |
|
|
Zhangheng
|
12de7fb1f6
|
Remove the HiMambaRadixTree that is no longer in use (#33468)
|
2026-08-07 23:01:40 +08:00 |
|
|
Xiaoyu Zhang
|
d4be483efb
|
[diffusion] Enable breakable CUDA graph for LTX-2 (H200 two-stage e2e 10.75 s -> 6.90 s, 1.56x) (#33885)
|
2026-08-07 22:29:14 +08:00 |
|
|
|
bc148dfdc8
|
[diffusion] feat: make scheduler rpc deadlines explicit (#33965)
Co-authored-by: suoyf <suoyf@nscc-tj.cn>
Co-authored-by: Mick <mickjagger19@icloud.com>
|
2026-08-07 21:33:23 +08:00 |
|
|
danielafrimi
|
4020bc95a7
|
Fix Nemotron W4A16 NVFP4 MoE backend (#33543)
Signed-off-by: dafrimi <dafrimi@nvidia.com>
|
2026-08-07 12:00:28 +00:00 |
|
|
Mick
|
5ca734fc3d
|
[diffusion] UX: speed up tp and fsdp checkpoint loading (#33960)
|
2026-08-07 19:23:30 +08:00 |
|
|
Dayananda V
|
1034977318
|
[diffusion] fix: bind each rank to accelerator before distributed init (#33054)
|
2026-08-07 19:01:58 +08:00 |
|
|
Yihao WangandClaude Opus 5
|
acb64db9e2
|
[diffusion] fix: enable bcg with tp (#33421)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-08-07 19:01:05 +08:00 |
|
|
|
fe52b49827
|
Fix IndexError in Triton backend with pipeline parallelism (#30340)
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
Co-authored-by: Shangming Cai <csmthu@gmail.com>
|
2026-08-07 18:58:04 +08:00 |
|
|
Lennox FuandMick
|
7af3d000f2
|
[diffusion] feat: gate /health and /health_generate on warmup completion and add liveness endpoint (#33787)
Co-authored-by: Mick <mickjagger19@icloud.com>
|
2026-08-07 17:59:23 +08:00 |
|
|
Pan LiandMick
|
a42683eb62
|
[diffusion] model: support lingbot-video moe 30b t2v (#32341)
Signed-off-by: Pan Li <pandalee@ustc.edu>
Co-authored-by: Mick <mickjagger19@icloud.com>
|
2026-08-07 17:57:01 +08:00 |
|
|
MickandClaude Fable 5
|
13938fed3f
|
[diffusion] feat: make ring admission a backend capability (#33928)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-08-07 17:55:44 +08:00 |
|
|
MickandClaude Fable 5
|
28b43bf693
|
[diffusion] perf: build qwen's masked varlen metadata host-side (#33954)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-08-07 17:55:15 +08:00 |
|
|
Xiaoyu ZhangandClaude Fable 5
|
572434e2f6
|
[diffusion] Z-Image bit-exact fused qk-norm (H200 Turbo 1024px e2e -6.4%) (#33886)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-08-07 17:03:28 +08:00 |
|
|
Baizhou Zhang
|
5e60363960
|
Fix prefill CP graph overflow with larger bucket search (#33906)
|
2026-08-07 01:33:14 -07:00 |
|
|
Liangsheng Yin
|
7395ee833e
|
[CI] Share VLM engines and prune launch matrices on the per-commit H100/H200 suites (#33944)
|
2026-08-07 01:22:22 -07:00 |
|
|
Trevor Morris
|
3ed2a0adf3
|
feat: Add flashinfer mHC fusion for DSV4 (#33616)
|
2026-08-07 08:01:33 +00:00 |
|
|
MickandClaude Fable 5
|
85d611a055
|
[diffusion] fix: scope the masked-path replicated guard to sp runs (#33953)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-08-07 15:45:50 +08:00 |
|
|
weireweireandweireweire
|
5e58af1503
|
Fix fractional simulated acceptance in DSpark (#33463)
Co-authored-by: weireweire <20922698+weireweire@users.noreply.github.com>
|
2026-08-07 00:45:07 -07:00 |
|
|
Mick
|
9aadacfc53
|
[diffusion] CI: exercise the default sp selection in CI (#33931)
|
2026-08-07 14:20:19 +08:00 |
|
|
triple-mu
|
a79340dedd
|
[diffusion] fix: minimax-h3 text encoder device mismatch under --text-encoder-cpu-offload (#33864)
|
2026-08-07 14:04:20 +08:00 |
|
|
Leon Gao
|
4d4f8023c4
|
[srt] Batch scheduler cache frees (#33475)
|
2026-08-06 21:49:59 -07:00 |
|
|
Mick
|
c2657cc4bf
|
[diffusion] refactor: gate fast vae paths by quality (#33849)
|
2026-08-07 12:39:55 +08:00 |
|
|
WenhaoZhang
|
914644e81c
|
[diffusion] fix: fix 4/8-step distilled minimax-h3 turbo lora merge (#33875)
|
2026-08-07 12:38:37 +08:00 |
|
|
MickandClaude Fable 5
|
6dc77e490d
|
[diffusion] chore: route zimage and hunyuanvideo attention through USPAttention (#33923)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-08-07 12:36:23 +08:00 |
|
|
MickandClaude Fable 5
|
698f019a5a
|
[diffusion] chore: derive h3 attention admission from backend capabilities (#33707)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-08-07 12:35:15 +08:00 |
|
|
Liangsheng Yin
|
afa79330b8
|
[misc] Remove break-graph debug log; reclaim pid-less /dev/shm leaks in CI (#33929)
|
2026-08-06 21:18:01 -07:00 |
|
|
Liu Zhenlong
|
453ea21dd3
|
fix(qwen2_5vl): replace in-place += with out-of-place + on expand view in decode path (#22634)
|
2026-08-07 11:51:09 +08:00 |
|
|
|
f9e6888b5a
|
[Distributed] Propagate semantic group names to PyTorch process groups (#32900)
Co-authored-by: jipengtian <jipengtian@xiaohongshu.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-08-06 20:38:12 -07:00 |
|
|
|
c54dc4582f
|
[Diffusion]Skipping tensor copying for non-BCG GLM-Image workflows (#33688)
Co-authored-by: Elizaveta Martirosian <elizaveta.martirosian@gmail.com>
Co-authored-by: ronnie_zheng <zl19940307@163.com>
|
2026-08-07 06:19:58 +03:00 |
|
|
Nikhil KulkarniandClaude Opus 5
|
fe6a05a8e8
|
fix: preserve priority for batched embedding requests (#32977)
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
|
2026-08-06 19:26:18 -07:00 |
|
|
Yuwei An
|
db8f3cdd11
|
fix(gdn): skip the -1 padding sentinel in the chunked extend kernel (#33810)
|
2026-08-06 18:48:47 -07:00 |
|
|
MickandClaude Fable 5
|
1e08b865f9
|
[diffusion] feat: support K/V-gather style sequence parallel (CP-like) attention (#32667)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-08-07 09:39:28 +08:00 |
|
|
Mick
|
9ee658d4f6
|
[diffusion] CI: fix output-rank test fixture (#33878)
|
2026-08-07 09:33:50 +08:00 |
|
|
Dustin LuongandJimmy Shong
|
2c3ecf32f1
|
[Fix] Reformat /vertex_generate successful predictions (#33446)
Co-authored-by: Jimmy Shong <69131491+Jiminator@users.noreply.github.com>
|
2026-08-07 00:00:48 +00:00 |
|
|
Hao Zhangandzhisbug
|
af7c62e337
|
Fix paged SWA retraction resume accounting (#33794)
Co-authored-by: zhisbug <1654062+zhisbug@users.noreply.github.com>
|
2026-08-06 16:32:54 -07:00 |
|
|
Po-Han Huang (NVIDIA)
|
bae29f716a
|
Fix inference mode mismatch in FlashInfer warmup (#33788)
|
2026-08-06 16:11:41 -07:00 |
|
|
Oguz UlgenandLianmin Zheng
|
b38caebf09
|
[AMD] Enable gfx1250 sgl-kernel builds (#32466)
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
|
2026-08-06 15:47:17 -07:00 |
|
|
valechen
|
18e6c61c21
|
[AMD] perf: compact Triton extend-attention for ragged prefill (AMD/HIP-only) (#29677)
|
2026-08-06 14:46:10 -07:00 |
|
|
Brayden Zhong
|
dd7e4c91e2
|
Fix Mistral-Large-3 EAGLE draft skipping DeepseekV2Model.__init__ (#33785)
|
2026-08-06 13:59:28 -07:00 |
|