 Alison Shao
|
3f4fbc165d
|
Upgrade CI default CUDA version from 12.9 to 13.0 (#21441)
|
2026-04-12 21:48:40 -07:00 |
|
|
Mohammad Miadh Angkad
|
4dbd59850b
|
Add bfloat16 KV cache validation for HiSparse (#22505)
|
2026-04-13 12:41:42 +08:00 |
|
|
Xiaoyu Zhang
|
fae0a2fc3c
|
[codex] Add LTX-2.3 benchmark skill recipes (#22631)
|
2026-04-13 12:23:32 +08:00 |
|
|
Liangsheng Yin
|
c775c31cb3
|
Simplify test_chunked_prefill; remove redundant tests (#22652)
|
2026-04-12 20:26:54 -07:00 |
|
|
Mick
|
bf022e177c
|
Revert "[Diffusion] Add FLUX.1-dev ModelOpt NVFP4 support (#22574)" (#22649)
|
2026-04-13 11:17:32 +08:00 |
|
|
|
bc59cc0f96
|
[RaidxTree Refactor]: Support Unified HybridRadixTree V2 (#21206)
Co-authored-by: ispobock <ispobaoke@gmail.com>
Co-authored-by: pansicheng <sicheng.pan.chn@gmail.com>
Co-authored-by: yizhang2077 <1109276519@qq.com>
Co-authored-by: xiezhq-hermann <xiezhq@stanford.edu>
|
2026-04-13 10:28:22 +08:00 |
|
|
Ziang Li
|
5593539942
|
[RL] Refactor NVFP4 shuffling/swizzling to in-place replacement (#22204)
|
2026-04-12 19:08:45 -07:00 |
|
|
blzhengandMa Mingfei
|
934e19a610
|
[CPU] Fix argument issues in qkv_proj_with_rope_fused_weight and bmm… (#21367)
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
|
2026-04-13 09:59:13 +08:00 |
|
|
Liangsheng Yin
|
da6b8e1448
|
Extract pause_resume_in_place kit; rename test_abort to test_scheduler_control (#22647)
|
2026-04-12 18:49:37 -07:00 |
|
|
Lawrence Wu
|
28e40d873c
|
fix(PD): respect pause_generation in disagg event loops (#20908)
|
2026-04-12 18:07:51 -07:00 |
|
|
|
c1ab68b45e
|
fix: streaming session race condition + some metrics (#21875)
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: hnyls2002 <lsyincs@gmail.com>
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
|
2026-04-12 18:05:23 -07:00 |
|
|
Xiaoyu Zhang
|
37fc47c645
|
diffusion: fix layerwise offload for ModelOpt quantized DiTs (#22594)
|
2026-04-13 08:01:54 +08:00 |
|
|
Xiaoyu Zhang
|
03a1a7b81c
|
[Diffusion] Add FLUX.1-dev ModelOpt NVFP4 support (#22574)
|
2026-04-13 07:57:41 +08:00 |
|
|
Kurt ShusterandYusheng Su
|
f81b6df3a3
|
[lora] Fix partial MoE rank loading, VL lm_head, strict loading, deepseek on-demand (#21864)
Co-authored-by: Yusheng Su <yushengsu.thu@gmail.com>
|
2026-04-12 16:25:02 -07:00 |
|
|
Khoa PhamandClaude Opus 4.6
|
1f8df97054
|
Fix broken streaming response with --incremental-streaming-output (#22549)
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
2026-04-12 15:05:58 -07:00 |
|
|
Mohammad Miadh Angkad
|
701a0e0c25
|
[CI/Docker] Clean up redundant flashinfer cubin downloads (#22491)
|
2026-04-12 12:30:41 -07:00 |
|
|
ZhiyuandClaude Opus 4.6
|
d4ad30b94c
|
[diffusion] quant: enable modelopt quantized FLUX deployment (#20082)
Signed-off-by: Zhiyu Cheng <zhiyuc@nvidia.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
2026-04-12 23:35:33 +08:00 |
|
|
Mick
|
495ef8ec64
|
[diffusion] model: support LTX2.3 two stage (#22182)
|
2026-04-12 22:15:57 +08:00 |
|
|
Ziang Li
|
31453bb76a
|
[RL] Fix weight update for mxfp8 flashinfer_cutlass gemm backend (#22484)
|
2026-04-12 13:02:17 +00:00 |
|
|
Mohammad Miadh Angkad
|
bcc0c65aa8
|
[DSA] Hopper FP8 FlashMLA KV padding (#22372)
|
2026-04-12 02:19:17 -07:00 |
|
|
Kurt Shuster
|
0e0091c6c8
|
[server] Add --quantization unquant to explicitly opt out of quantization (#21863)
|
2026-04-12 02:17:22 -07:00 |
|
|
Wenyao Gao
|
4dfc8e1c3f
|
VLM: support passing --mm-process-config for all models (#18467)
|
2026-04-12 17:08:05 +08:00 |
|
|
Liangsheng Yin
|
f1eb4ca90c
|
Fix streaming session busy check double-counting; add compat CI tests (#22213)
|
2026-04-12 01:48:16 -07:00 |
|
|
Xinyuan Tong
|
3f60df8012
|
[Test] Fix flaky test_function_call_specific by adding strict=True (#22624)
|
2026-04-12 01:22:57 -07:00 |
|
|
Ke Bao
|
bc1bfbf607
|
Fix swa input length limitation (#22597)
|
2026-04-12 16:03:35 +08:00 |
|
|
Liangsheng Yin
|
f2377a00cb
|
Add SWA support for runtime busy memory check (#21499)
|
2026-04-12 00:39:51 -07:00 |
|
|
wufann
|
19cb918653
|
[Not-Merge][AMD] GLM-5 performance optimization (#21166)
|
2026-04-11 23:58:11 -07:00 |
|
|
Hubert LuandHAI
|
edaa5973d4
|
[AMD][No-Merge] Simplify fused allreduce + RMSNorm and remove hidden_dim allowlist (#21986)
Co-authored-by: HAI <hixiao@gmail.com>
|
2026-04-11 23:47:08 -07:00 |
|
|
Xinyuan Tong
|
9a4e8089ff
|
[Whisper] Batch encoder forward for concurrent prefill requests (#22361)
|
2026-04-12 14:15:14 +08:00 |
|
|
Zhai Feiyue
|
52750129ef
|
fix prefill tps log accuracy (#22497)
|
2026-04-11 23:07:30 -07:00 |
|
|
Alex NailsandClaude Opus 4.6
|
c6fd9a00c7
|
[tokenizer] eliminate O(n²) copy in non-incremental streaming (#22567)
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
2026-04-11 23:05:36 -07:00 |
|
|
|
45472d70cc
|
[diffusion] CI: dynamic load-balanced partitioning for diffusion CI (#15528)
Co-authored-by: daiweitao <dwti614707404@163.com>
Co-authored-by: SGLang CI <ci@sglang.ai>
|
2026-04-12 13:02:43 +08:00 |
|
|
Alison ShaoandAlison Shao
|
d6c9d9116b
|
[CI] Update B200 est_times to prevent timeouts on slower machine (#22609)
Co-authored-by: Alison Shao <alison.shao@MacBook-Pro-D2W773R9CD.local>
|
2026-04-11 21:40:34 -07:00 |
|
|
Alison ShaoandAlison Shao
|
f21d23a211
|
ci: use local NVIDIA wheels to avoid re-downloading ~2GB every CI run (#22602)
Co-authored-by: Alison Shao <alison.shao@MacBook-Pro-D2W773R9CD.local>
|
2026-04-11 21:32:51 -07:00 |
|
|
Alison ShaoandAlison Shao
|
870a21bf39
|
[CI] Remove Slack bot from CI failure monitor (#21581)
Co-authored-by: Alison Shao <alison.shao@Mac.attlocal.net>
|
2026-04-11 20:34:48 -07:00 |
|
|
Aurick Qiao
|
cd2b2364ff
|
[Bugfix] fix model_config deletion (#22281)
|
2026-04-12 11:24:26 +08:00 |
|
|
Baizhou Zhang
|
2e70e4f4f6
|
[CI] Little renaming of gb200 CI workflow (#22608)
|
2026-04-11 17:52:42 -07:00 |
|
|
Kurt Shuster
|
8da1cfb30d
|
[lora][moe] Decoupled LoRA MoE backend with Marlin support (#21858)
|
2026-04-11 14:59:27 -07:00 |
|
|
Ziang Li
|
78043d4448
|
[Misc] [MXFP8] Drop sm100 mxfp8 warning (#21881)
|
2026-04-11 11:11:28 +00:00 |
|
|
Liangsheng Yin
|
61a62c6503
|
[mem] Flatten memory checkers into composable per-pool invariant checks (#22562)
|
2026-04-11 02:56:22 -07:00 |
|
|
dyhsup
|
8cca9747f5
|
[diffusion] model: support ERNIE-Image (#22439)
|
2026-04-11 17:18:11 +08:00 |
|
|
Liangsheng Yin
|
7ab94e438c
|
[Test] Fix flaky test_function_call_required by adding strict=True (#22586)
|
2026-04-11 02:14:22 -07:00 |
|
|
Baizhou Zhang
|
d14d368191
|
[Kernel] Set sgl_per_token_group_quant_8bit_v2 as default choice (#22467)
|
2026-04-11 01:59:57 -07:00 |
|
|
heziiop
|
4f45472f34
|
[NPU][Doc] add qwen3-30b-a3b low latency example (#22446)
|
2026-04-11 15:52:47 +08:00 |
|
|
|
f855a0bde6
|
Introduce CUDA graph debug mode with breakable CUDA graph (#19102)
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
Co-authored-by: Cheng Wan <chwan@rice.edu>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
|
2026-04-11 00:36:56 -07:00 |
|
|
Liangsheng Yin
|
d11da2403c
|
Add hisparse staging + decode offload guards to is_fully_idle() (#22577)
|
2026-04-11 00:12:10 -07:00 |
|
|
sushil DubeyandMa Mingfei
|
e26c73c4e9
|
[diffusion] platform: support Intel XPU (#17920)
Signed-off-by: sushil.dubey <sushil.dubey@intel.com>
Signed-off-by: Sushil Dubey <sushil.dubey@intel.com>
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
|
2026-04-11 15:09:02 +08:00 |
|
|
YC Yen-Ching TsengandHAI
|
3ce72252de
|
[AMD] Fix Timeout: stage-b-test-2-gpu-large-amd,stage-b-test-1-gpu-large-amd (#22228)
Co-authored-by: HAI <hixiao@gmail.com>
|
2026-04-10 22:55:44 -07:00 |
|
|
YC Yen-Ching Tseng
|
cf1436d6ae
|
[AMD] Diffusion - Enabel rocm miopen tuning on vae (#22428)
|
2026-04-10 22:47:25 -07:00 |
|
|
Jacob0226andClaude Opus 4.6
|
7e4e1dcd7a
|
[AMD] Fuse RMSNorm + FP8 per-token quant for GLM-4.7-FP8 (#21403)
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
|
2026-04-10 22:45:31 -07:00 |
|