 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 |
|
|
Mohammad Miadh Angkad
|
c2d90db1e3
|
[CI] Add Kimi-K3 low-latency performance check (#34089)
|
2026-08-08 13:42:59 -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 |
|
|
Mick
|
cf2d4fd679
|
docs: clarify K3 VLM feature transport (#34099)
|
2026-08-08 19:23:00 +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 |
|
|
Liangsheng Yin
|
2c0188cc78
|
[Fix] Give the piecewise CUDA graph test stub an hf_config (#34100)
|
2026-08-08 02:04:16 -07:00 |
|
|
Liangsheng YinandBaizhou Zhang
|
f6a6f5bf1e
|
[CI] Trim redundant nightly test registrations (#34070)
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
|
2026-08-08 01:42:46 -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 |
|
|
xdtbynd
|
e732c0a9dc
|
[UT][NPU] add unit tests for ascend_torch_native_backend and mla_preprocess (#32505)
|
2026-08-08 16:15:12 +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 |
|
|
Baizhou Zhang
|
c9444deef4
|
Docker: install DeepEP from release wheels (#34041)
|
2026-08-07 23:51:09 -07:00 |
|
|
Eric ZhangandClaude Opus 5
|
c69d59395b
|
[inkling] Render tool-result media instead of coercing content to str (#33898)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-08-08 14:39:19 +08:00 |
|
|
Aurick Qiao
|
6185ed8011
|
Add registered short-conv tests and backend extensions (#34045)
|
2026-08-08 14:38:03 +08:00 |
|
|
Thomas Wang
|
6679d9b60c
|
[AMD] Add K3 verified mla kernel for DSpark on triton backend (#33981)
|
2026-08-07 22:59:26 -07:00 |
|
|
Cheng Wan
|
b61a06921e
|
moe: the shared-experts-fusion decision is a per-runner value the loader installs (#33889)
|
2026-08-07 22:42:58 -07:00 |
|
|
Cheng Wan
|
eda0ddc260
|
config: delete the dead get_server_args() bindings across the repo (#33888)
|
2026-08-07 22:41:53 -07:00 |
|
|
Cheng Wan
|
a5af27f49e
|
config: retire ServerArgs.derive; per-runner values are constructor arguments (#33887)
|
2026-08-07 22:41:09 -07:00 |
|
|
Xiaoyu ZhangandClaude Fable 5
|
5dffa06fe1
|
[diffusion] GLM-Image bit-exact fused aten LayerNorm+modulate / qk-LN (H200 30-step denoise -8.1%) (#34008)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-08-08 13:26:11 +08:00 |
|
|
Xiaoyu Zhang
|
148f15b0af
|
[diffusion] FLUX.1 fused adaLN modulate (bit-exact) + RoPE cache hoist, LN-affine folding behind quality=high (H200 e2e -3.5% lossless / -6.9% high) (#34004)
|
2026-08-08 13:07:42 +08:00 |
|
|
|
f64328c7f6
|
[diffusion] feat: support quant-videogen prq kv-cache quantization (memory-saving) for causal-dit (#32581)
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
|
2026-08-08 12:56:54 +08:00 |
|
|
MickandClaude Fable 5
|
24c84dfa68
|
[diffusion] doc: add parallelism overview (#33704)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-08-08 11:36:06 +08:00 |
|
|
RunningLeonandXinyuan Tong
|
55f02e6887
|
Support Intern-S2-Mobius (#33691)
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
|
2026-08-08 11:06:57 +08:00 |
|
|
MickandClaude Fable 5
|
a25c330eb1
|
[diffusion] feat: cross-node sequence parallelism (Ulysses x Ring) (#33327)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-08-08 10:56:28 +08:00 |
|
|
MickandClaude Fable 5
|
52afe87a08
|
[diffusion] fix: stop runai-model-streamer's rank-discovery collective from firing on independent per-rank loads (#33969)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-08-08 08:54:08 +08:00 |
|
|
paulzhang-tm
|
209857334e
|
[Scheduler] Gate SWA eviction on accumulated tokens (#33404)
|
2026-08-08 08:28:26 +08:00 |
|
|
Ke Bao
|
633838b0ec
|
Add the 8-gpu Inkling consistency test (#34009)
|
2026-08-08 08:24:08 +08:00 |
|
|
Ke Bao
|
ce84df0fa1
|
Fix deterministic inference for Inkling (#33417)
|
2026-08-08 07:48:15 +08:00 |
|
|
Joe RowellandJimmy Shong
|
1d812865dc
|
[Laguna] fix YaRN mscale double-application in rope config (#33558)
Co-authored-by: Jimmy Shong <69131491+Jiminator@users.noreply.github.com>
|
2026-08-07 16:46:08 -07:00 |
|
|
Liangsheng Yin
|
c59d2b4329
|
[Fix] Judge the phase-checker device-assert test by its FAIL line, not the exit code (#34017)
|
2026-08-07 16:19:05 -07:00 |
|
|
Douglas YangandClaude Opus 5
|
86f373daff
|
docs(cookbook): DeepSeek-V4-Flash-0731 — drop chunked-prefill/autotune flags on B300 low-latency (#34044)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-08-07 23:12:56 +00:00 |
|
|
Zhiqiang Xie
|
3dc91366ac
|
[HiCache] write_back: reclaim duplicated host copy first under host pressure (#33777)
|
2026-08-07 15:59:59 -07:00 |
|
|
Baizhou Zhang
|
eb3cc879e0
|
Install DeepEP from release wheels (#33932)
|
2026-08-07 15:38:44 -07:00 |
|