 Khoa Pham
|
ee3ee8393c
|
fix: preserve GQA head mapping in Triton DCP prefill (#34161)
|
2026-08-09 18:52:18 -07:00 |
|
|
Xiaoyu ZhangandClaude Opus 4.8
|
441910f926
|
[diffusion] LTX-2 quality=high fused RMSNorm+modulate + FFN GELU epilogue (H200 ltx23-one-stage denoise 45.85->43.24 s, ~matches torch.compile) (#34172)
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
|
2026-08-10 09:46:17 +08:00 |
|
|
Mick
|
c20e99bd22
|
fix(vlm): preserve Kimi-K3 GPU JPEG accuracy (#34163)
|
2026-08-10 09:42:52 +08:00 |
|
|
|
553dc0f936
|
[MLX] Support gpt-oss: sliding-window attention, attention sinks, sm_scale (#30050)
Co-authored-by: R0CKSTAR <yeahdongcn@gmail.com>
Co-authored-by: Alex Nails <alex.nails@radixark.ai>
|
2026-08-09 18:32:36 -07:00 |
|
|
Ke Bao
|
25b7015064
|
Fix stale track rows corrupting conv checkpoints under the prefill graph (#34184)
|
2026-08-10 08:57:23 +08:00 |
|
|
Xiaoyu ZhangandClaude Opus 4.8
|
56ef810cad
|
[diffusion] BCG: auto-capture the default warmup resolution instead of hard-requiring --warmup-resolutions (H200 SANA denoise 0.73->0.457 s with a single flag) (#34174)
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
|
2026-08-10 08:37:32 +08:00 |
|
|
Liangsheng Yin
|
7c90840bad
|
[CI] Key scheduled CUDA suites by runner_config instead of hand-written jobs (#34186)
|
2026-08-09 16:44:53 -07:00 |
|
|
Liangsheng YinandDeleter-D
|
4a5d7d3c67
|
[DSV4] Fix silent KV corruption when speculative draft tokens > 4 (#34189)
Co-authored-by: Deleter-D <867909454@qq.com>
|
2026-08-09 15:54:41 -07:00 |
|
|
Cheng Wan
|
b4284f3eb7
|
config: the KV-cache configurator reads the bags (#34096)
|
2026-08-09 14:45:42 -07:00 |
|
|
Cheng Wan
|
e216c2bc59
|
config: the runner and scheduler read resolved config from the bags (#34095)
|
2026-08-09 14:45:11 -07:00 |
|
|
Cheng Wan
|
63833f8034
|
config: business code no longer reads the published ServerArgs (#34081)
|
2026-08-09 14:44:08 -07:00 |
|
|
Cheng Wan
|
110bf7e6a8
|
config: retire the hidden global fallbacks and the mamba-extra-buffer instance reads (#34080)
|
2026-08-09 14:43:28 -07:00 |
|
|
|
bfeb9a8af2
|
[feat] Add language_model_only parameter support for Qwen35 (#22867)
Co-authored-by: 瑀澈 <yuche.lz@alibaba-inc.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
|
2026-08-10 02:47:36 +08:00 |
|
|
Eric Zhang
|
168eba3257
|
[Fix] Speculative decoding crashes with DP-Attention (#33892)
|
2026-08-10 00:56:36 +08:00 |
|
|
Kurt ShusterandClaude Fable 5
|
3fe65e0654
|
Deterministic gumbel sampling: clamp u=1 so masked tokens can't be sampled (#33423)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-08-09 21:43:27 +08:00 |
|
|
Eric Zhang
|
fc40684b32
|
[srt] Fix sconv state memory corruption on specdec (#34043)
|
2026-08-09 21:42:54 +08:00 |
|
|
|
11d03eaeef
|
runtime: Add flashinfer rmsnorm + quant fusion support SM90, SM100, SM120- #32994 (#33471)
Signed-off-by: Devashish Lal <devcode@fb.com>
Co-authored-by: Devashish Lal <devcode@fb.com>
Co-authored-by: Xiaoyu Zhang <1182563586@qq.com>
|
2026-08-09 20:15:03 +08:00 |
|
|
Yuzhen Zhou
|
7120f3ee13
|
fix: support FA4 backend for GLM4.7-flash (#33436)
|
2026-08-09 20:05:38 +08:00 |
|
|
Lianmin Zheng
|
71043b9dbb
|
Revert parallel request lifecycle tracking from #32588 (#34160)
Signed-off-by: Lianmin Zheng <lianminzheng@gmail.com>
|
2026-08-09 03:10:02 -07:00 |
|
|
Ke Bao
|
fcc5468cce
|
Fix deterministic inference all-reduce for tp>1 (#34159)
|
2026-08-09 18:08:14 +08:00 |
|
|
Leon Gao
|
78cd60b4e3
|
[srt] Reuse batched Mamba boundary mask (#33477)
|
2026-08-09 16:47:05 +08:00 |
|
|
WenhaoZhang
|
51470b376f
|
[diffusion] feat: support sol-attn sparse attention backend for h3 (#33702)
|
2026-08-09 16:26:06 +08:00 |
|
|
Khoa PhamandClaude Opus 5
|
ce1b9f88b6
|
config: derive the runner's DCP topology from its ParallelState (#34133)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-08-09 01:18:24 -07:00 |
|
|
Mick
|
22e003580b
|
[Kimi K3] optimize: preprocess cpu-transport images on the vision owner (#33921)
|
2026-08-09 16:13:20 +08:00 |
|
|
Kangrui Du
|
d0aa37b49b
|
[diffusion] fix: update weight from tensor detects device by uuid (#32685)
|
2026-08-09 16:11:28 +08:00 |
|
|
Lianmin Zheng
|
bc285b2064
|
refactor: clean up logits processor helpers (#34158)
|
2026-08-09 00:22:57 -07:00 |
|
|
Xiaoyu Zhang
|
f6cbdc1dd1
|
docs(diffusion): refresh skills for latest runtime (#34143)
|
2026-08-09 10:30:46 +08:00 |
|
|
Xiaoyu Zhang
|
38c007dfe5
|
[diffusion] FLUX.1: route the adaLN LN+modulate sites through the bit-exact fused LayerNorm+modulate kernel (H200 1024^2 lossless denoise -1.2%, e2e wall -2.9%) (#34126)
|
2026-08-09 09:52:37 +08:00 |
|
|
Xiaoyu ZhangandClaude Fable 5
|
6424fec326
|
[diffusion] Bit-exact data-movement elimination for the Wan causal VAE decoder (H200 LongLive2 704x1280x61f: decode 2.80->2.32 s lossless / 2.12->1.67 s quality=high, e2e -10.7%) (#34125)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-08-09 09:50:56 +08:00 |
|
|
Xiaoyu ZhangandClaude Fable 5
|
33ed5d4413
|
[diffusion] perf_logger: SYNC_STAGE_PROFILING must drain the GPU queue for stage records too (fixes 2-3x inflated DecodingStage readings) (#34124)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-08-09 09:49:52 +08:00 |
|
|
Yuankai Chen
|
cea16bf229
|
Fix Qwen3-MoE producing garbage with the mori a2a backend (#34006)
|
2026-08-08 15:44:01 -07:00 |
|
|
Wang, FangYuan
|
ba7abd4f92
|
[AMD] Support DeepSeek V4 DSpark on AMD HIP platform (#30964)
|
2026-08-08 15:22:14 -07:00 |
|
|
|
a59bb931c6
|
Fix DCP KV head mapping for GQA models (#32858)
Co-authored-by: Khoa Pham <khoa.pham@radixark.ai>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-08-08 14:25:09 -07:00 |
|
|
Diya Peng
|
c4f018ba1d
|
[Refactor] Separate ROCm-specific DeepSeek MHA and MLA forward paths (#31531)
|
2026-08-08 13:39:36 -07:00 |
|
|
Brayden Zhong
|
3fbb5330c7
|
Fix the router GEMM inaccuracy when using _front_w in Kimi-K3 (#33764)
|
2026-08-08 19:23:40 +00:00 |
|
|
Xiaoyu Zhang
|
dc9624deb2
|
[diffusion] Clean up kernels and shared fast paths (#34085)
|
2026-08-09 00:37:00 +08:00 |
|
|
Mohammad Miadh AngkadandBBuf
|
ec5199b906
|
[jit_kernel] Fix missing JIT kernel namespaces (#34106)
Co-authored-by: BBuf <1182563586@qq.com>
|
2026-08-08 22:15:05 +08:00 |
|
|
Eric ZhangandClaude Opus 5
|
f3ed82b3a8
|
[inkling] Let Anthropic thinking=disabled map to reasoning effort "none" (#33913)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-08-08 21:59:32 +08:00 |
|
|
|
548ff545c5
|
[diffusion] fix: guard sage attention sm90 bindings (#34107)
Co-authored-by: RunFMe <RunFMe@users.noreply.github.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
|
2026-08-08 21:32:40 +08:00 |
|
|
Mick
|
db75dfe10f
|
fix: always capture default prefill CUDA graph (#33352)
|
2026-08-08 19:24:49 +08:00 |
|
|
Leon Gao
|
cfb354bcfc
|
[Bugfix] Fix batched KV free aliasing (#34067)
|
2026-08-08 03:34:44 -07:00 |
|
|
Liangsheng Yin
|
a1ca76b24b
|
[Scheduler] Unify WAR read-done gating behind shared-read boundary declarations (#34052)
|
2026-08-08 03:26:36 -07:00 |
|
|
|
dd5d82bead
|
[NPU] Improve the execution efficiency and maintainability of pr‑test‑npu (#33724)
Co-authored-by: Even Zhou <even.y.zhou@outlook.com>
Co-authored-by: sglang-npu-bot <sglangnpu@163.com>
|
2026-08-08 16:42:44 +08:00 |
|
|
DarkSharpnessandClaude Fable 5
|
4ad5bb5d9a
|
[jit_kernel] Move JIT kernels into namespace sglang (#33400)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-08-08 16:10:15 +08:00 |
|
|
Yuan Luo
|
5fdf6cd18f
|
[MoE] Single-launch moe_align for tiny batches with many experts (#32395)
|
2026-08-08 16:08:25 +08:00 |
|
|
Xiaoyu ZhangandClaude Fable 5
|
891445676c
|
[diffusion] Sana: bit-exact fused aten LayerNorm+modulate under BCG (H200 denoise -4.8%) (#34015)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-08-08 16:05:25 +08:00 |
|
|
Mick
|
d747bd052e
|
feat(vlm): auto-select cuda vmm on multi-node mnnvl (#33936)
|
2026-08-08 16:00:58 +08:00 |
|
|
Mick
|
db3898fec1
|
fix: avoid piecewise prefill graph for trtllm_mla (#32785)
|
2026-08-08 16:00:10 +08:00 |
|
|
Sam ShleiferandClaude Fable 5
|
afb4f37ca5
|
[Inkling] silu_and_mul: replace helion kernels with plain Triton (#33903)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-08-08 15:00:23 +08:00 |
|
|
Sam ShleiferandClaude Fable 5
|
d238e36b24
|
[Fix] Restore data_parallel_rank alias on native /generate (dp-aware gateway routing is silently dropped) (#33565)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-08-08 14:59:16 +08:00 |
|