 cen121212
|
b1e1fe8eee
|
【NPU】【bugfix】accuracy fix when enable both nsa cp and prefixcache (#23268)
|
2026-04-28 09:08:28 +08:00 |
|
|
看海的人
|
9ffc0cc67e
|
[NPU] Support GLM-4.5V (#22961)
|
2026-04-28 09:08:19 +08:00 |
|
|
PiteXChenandZhiqiang Xie
|
4a04a9818e
|
【hicache】Optimize HiCache prefetch logic: adapt to remaining available memory when memory is insufficient (#16370)
Signed-off-by: CLFutureX <chenyongqyl@163.com>
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
|
2026-04-27 17:18:35 -07:00 |
|
|
Byron Hsuandroot
|
27659ea8c8
|
[PD+Pause] Remove redundant post processing (#23886)
Co-authored-by: root <root@slurm-h200-206-011.slurm-compute.tenant-slurm.svc.cluster.local>
|
2026-04-27 17:01:26 -07:00 |
|
|
|
cb0429f253
|
[Disagg] Finalize routed_experts_output in process_batch_result_disagg_prefill (#23885)
Co-authored-by: Byron Hsu <byron@periodiclabs.ai>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-04-27 16:40:05 -07:00 |
|
|
Pai Liu
|
7b9ff79f93
|
docs: update Python prerequisite to 3.10 (#23801)
|
2026-04-27 15:36:38 -07:00 |
|
|
Alison Shao
|
b73c44b545
|
test: relax TestMLADeepseekV3.test_gsm8k threshold 0.62 -> 0.60 (#23879)
|
2026-04-27 15:27:15 -07:00 |
|
|
Bi Xue
|
41181b6238
|
[sgl] copy mm_input in piecewise cuda graph when eagle3 is on (#23613)
|
2026-04-27 13:35:19 -07:00 |
|
|
Kurt ShusterandEthan Su
|
f34c20af86
|
[VLM] Fix Kimi-K2.5 CPU path: rename grid_thws -> image_grid_thw (#23501)
Co-authored-by: Ethan (Yusheng) Su <yushengsu.thu@gmail.com>
|
2026-04-27 20:34:28 +00:00 |
|
|
Vladislav Nosivskoy
|
28ee08c172
|
[HiCache] Add synchronization for context parallelism (#20460)
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
|
2026-04-28 02:13:07 +08:00 |
|
|
Xinyuan Tong
|
f34222da1b
|
[Docs] add cookbook for MiMo-V2.5 family (#23851)
|
2026-04-28 01:38:41 +08:00 |
|
|
Xinyuan Tong
|
96b0c64c88
|
Add docs_new code owner (#23855)
|
2026-04-27 10:31:35 -07:00 |
|
|
Jonah BernardandJonah Bernard
|
4fc5ebf0b7
|
[Chore] Remove deadcode in prefill delayer (#23389)
Co-authored-by: Jonah Bernard <96398205+Jonahcb@users.noreply.github.com>
|
2026-04-27 09:59:36 -07:00 |
|
|
1874.
|
47b8eadbc4
|
[Docs] Update Ascend NPU GGUF quantization documentation (#23845)
|
2026-04-27 17:30:24 +03:00 |
|
|
ranjiewen
|
f2b84b90ac
|
[npu]fix: qwen3-next w8a8 precision bugs (#21698)
|
2026-04-27 18:14:33 +08:00 |
|
|
Lianmin Zheng
|
8536d4b402
|
Clean up noisy startup warnings from third-party deps (#23669)
|
2026-04-27 03:10:46 -07:00 |
|
|
amote-i
|
06725ecf0d
|
[NPU] [DOC] Add support new models doc for NPU (#23824)
|
2026-04-27 17:13:23 +08:00 |
|
|
Shenxiu LiuandXinyuan Tong
|
a3fc982ba7
|
[Whisper] Automatic language detection via structured generation (#22997)
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
|
2026-04-27 15:54:41 +08:00 |
|
|
zijiexia
|
c2ec64f243
|
docs: verify GB300 Pro DeepSeek V4 recipes (#23817)
|
2026-04-27 00:21:26 -07:00 |
|
|
Xiaoyu Zhang
|
5f47cae1a0
|
add H100 configs for GLM-4.7-Flash (#23719)
|
2026-04-27 15:07:39 +08:00 |
|
|
Yujing
|
9ec4aa1b5c
|
[Doc]Add msprobe doc in docs_new path (#23712)
|
2026-04-27 10:06:50 +03:00 |
|
|
Colin Z
|
d49561b8ae
|
[AMD] Fix Kimi-K2.6 Quark MXFP4 loading prefix and packed module mapping (#23408)
|
2026-04-26 23:56:15 -07:00 |
|
|
Praneth Paruchuri
|
b7113cadb1
|
[Bug Fix] Reject pp_max_micro_batch_size=0 to prevent silent deadlock on generate() (#23799)
|
2026-04-27 13:36:04 +08:00 |
|
|
Xinyuan Tong
|
e5198386bd
|
Upgrade transformers from 5.5.4 to 5.6.0 (#23525)
|
2026-04-26 22:33:54 -07:00 |
|
|
Zheng Wengang
|
91825b8808
|
[FEAT][EPD] support encoder real health (#23343)
|
2026-04-27 13:21:28 +08:00 |
|
|
AMD-yanfeiwang
|
5141d8ae21
|
[AMD]fix: use CUDA event for targeted draft-to-verify sync in EAGLE overlap (#21940)
|
2026-04-26 21:58:34 -07:00 |
|
|
Bingxu Chen
|
d84470079d
|
[AMD] Fix Grok-2 nightly: avoid multimodal misdetection from auto-populated vision_config (#23383)
|
2026-04-26 21:54:36 -07:00 |
|
|
zijiexia
|
c74b345e3a
|
[docs] Update FA4 support SWA (#23793)
|
2026-04-26 20:40:36 -07:00 |
|
|
Jia GuoandClaude Opus 4.7
|
bead2e3470
|
perf: optimize PCG inductor path for FP8 models (redo of #21734) (#23227)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-04-26 20:34:27 -07:00 |
|
|
|
85376a6119
|
refactor(moe): centralize post-experts all-reduce skip predicate (#23748)
Co-authored-by: Byron Hsu <byron@periodiclabs.ai>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-04-26 20:29:59 -07:00 |
|
|
sglang-botandsglang-bot
|
da175b964d
|
chore: update CI test est_time values (#23785)
Co-authored-by: sglang-bot <sglang-bot@users.noreply.github.com>
|
2026-04-26 20:17:50 -07:00 |
|
|
iridiumine
|
32c3513816
|
[NPU] Support MTP for Qwen3.5 (#20918)
|
2026-04-27 10:44:17 +08:00 |
|
|
Baizhou ZhangandClaude Opus 4.7
|
977830e91e
|
ci(deepseek-v4): add b300/grace-blackwell dev-branch build options (#23778)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-04-26 16:44:16 -07:00 |
|
|
Kangyan-ZhouandClaude Opus 4.7
|
35591c7d51
|
fix(lora): don't assert on non-LoRA lm_head adapter weights (#23433)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-04-26 12:10:07 -07:00 |
|
|
zijiexia
|
3d95ca7546
|
docs(DeepSeek-V4): mark gb200|big|low-latency verified (#23737)
|
2026-04-26 11:15:59 -07:00 |
|
|
Mick
|
a392ae8879
|
[diffusion] feat: accelerate multiple-outputs generation (#23759)
|
2026-04-27 01:47:33 +08:00 |
|
|
|
10fd0faccd
|
[CPU] Add Qwen3.5 model optimization for CPU (#19484)
Co-authored-by: Zheng, Beilei <beilei.zheng@intel.com>
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
|
2026-04-26 10:12:36 -07:00 |
|
|
Liwansi
|
7d49564431
|
[NPU]Fix support_triton bug (#23604)
|
2026-04-26 21:34:56 +08:00 |
|
|
Cheng WanandClaude Opus 4.7
|
c7878dbb6d
|
[MoE] Deprecate act_and_mul_triton; fold filter_expert into JIT silu/gelu_and_mul (#23707)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-04-26 01:41:35 -07:00 |
|
|
Mick
|
d49a0377de
|
[diffusion] refactor: make timestep scheduler request-local (#23716)
|
2026-04-26 15:59:53 +08:00 |
|
|
|
9003f24e2b
|
chore: bump sglang-kernel version to 0.4.1.post1 (#23733)
Co-authored-by: sglang-bot <sglang-bot@users.noreply.github.com>
Co-authored-by: Kangyan Zhou <zky314343421@gmail.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-04-25 23:23:49 -07:00 |
|
|
Kangyan-ZhouandClaude Opus 4.7
|
8efa177f1e
|
[CI] release-pypi-nightly: install protoc before building wheel (#23750)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-04-25 22:37:29 -07:00 |
|
|
Kangyan-ZhouandClaude Opus 4.7
|
4be853e1c6
|
[CI] release-whl-kernel: strip +cu129 local version before PyPI upload (#23749)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-04-25 22:14:45 -07:00 |
|
|
Ethan (Yusheng) Su
|
3cfd1561df
|
docs(DeepSeek-V4): add h200|big verified recipes + tune H200 Pro parameters (#23742)
|
2026-04-25 21:44:51 -07:00 |
|
|
Kangyan-ZhouandClaude Opus 4.7
|
282b47fcfd
|
[CI] release-whl-kernel: clean root-owned build artifacts before checkout (#23747)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-04-25 21:39:41 -07:00 |
|
|
Yuhao Yang
|
049f1bf6fb
|
docs(DeepSeek-V4): add GB200 platform to cookbook recipe (#23725)
|
2026-04-25 20:54:55 -07:00 |
|
|
|
ba4e9d2ac2
|
Apply should_use_dp_reduce_scatterv guard to remaining MoE models (follow-up to #23731) (#23732)
Co-authored-by: Byron Hsu <byronhsu@noreply.github.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-authored-by: Kangyan-Zhou <zky314343421@gmail.com>
|
2026-04-25 20:36:16 -07:00 |
|
|
|
71029abd64
|
Fix Qwen3 MoE: also guard EP all-reduce with not use_reduce_scatter (follow-up to #23731) (#23734)
Co-authored-by: Byron Hsu <byron@periodiclabs.ai>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-04-25 20:35:52 -07:00 |
|
|
|
714173555c
|
chore: bump sgl-kernel version to 0.4.1.post1 (#23720)
Co-authored-by: sglang-bot <sglang-bot@users.noreply.github.com>
Co-authored-by: Kangyan Zhou <kangyan.zhou@radixark.ai>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-04-25 17:13:02 -07:00 |
|
|
Byron HsuandByron Hsu
|
99b59b279c
|
Fix Qwen3 MoE double-reduce when DP attention + EP + reduce_scatterv (#23729) (#23731)
Co-authored-by: Byron Hsu <byronhsu@noreply.github.com>
|
2026-04-25 15:28:28 -07:00 |
|