 Xiaoyu Zhang
|
d633ab7349
|
[Diffusion] Add qknorm rope fuse kernel (#21440)
|
2026-03-27 14:27:08 +08:00 |
|
|
Xiaoyu Zhang
|
e8d46f145c
|
Opt jit qknorm_across_heads cuda kernel (#21503)
|
2026-03-27 13:30:46 +08:00 |
|
|
Johnsonms
|
8a56a7b04d
|
[jit_kernel] Migrate cast (downcast_fp8) from sgl-kernel AOT to JIT (#19103)
|
2026-03-27 13:21:44 +08:00 |
|
|
JohnsonmsandXiaoyu Zhang
|
c531be455e
|
[jit_kernel] Add fused_qknorm_rope JIT kernel (#19059)
Co-authored-by: Xiaoyu Zhang <35585791+BBuf@users.noreply.github.com>
|
2026-03-27 13:21:28 +08:00 |
|
|
Baizhou Zhang
|
0138129d3c
|
[CI] Fix nemotron nvfp4 test estimated time (#21516)
|
2026-03-26 21:53:09 -07:00 |
|
|
Mohammad Miadh Angkad
|
eaf392b9cc
|
Remove redundant DeepSeek V3 FP4 PCG test (#21485)
|
2026-03-26 21:52:47 -07:00 |
|
|
Shangming Cai
|
1487f80158
|
chore: bump mooncake version to 0.3.10 (#20942)
Signed-off-by: Shangming Cai <csmthu@gmail.com>
|
2026-03-27 10:35:31 +08:00 |
|
|
Mick
|
d7c4c57ace
|
[diffusion] refactor: move format-specific weight loading hooks (quant-related) to a dedicated file (#21366)
|
2026-03-27 09:58:49 +08:00 |
|
|
Liangsheng Yin
|
e1ee68d0fc
|
Release mm features on session close and support multiple /rerun-ut specs (#21501)
|
2026-03-26 18:31:29 -07:00 |
|
|
Aurick Qiao
|
c2b3e42ad6
|
Fix sessions with mm inputs (#21269)
|
2026-03-26 17:38:23 -07:00 |
|
|
Liangsheng Yin
|
8a4cdcd538
|
Simplify flush_cache: reject concurrent requests, remove client-side retry (#21490)
|
2026-03-26 16:31:04 -07:00 |
|
|
Liangsheng Yin
|
9dc266adb4
|
Fix concurrent /rerun-ut posting duplicate workflow URLs (#21495)
|
2026-03-26 16:26:00 -07:00 |
|
|
Liangsheng Yin
|
c580ddd19d
|
Fix benchmark generating empty prompts when random_input_len is small (#21492)
|
2026-03-26 16:24:35 -07:00 |
|
|
Baizhou Zhang
|
a93065679b
|
Revert "bugfix for weight loading for qwen3-next" (#21496)
|
2026-03-26 16:17:18 -07:00 |
|
|
SevenJ
|
2e65c27b29
|
Api add flush cache timeout (#21413)
Signed-off-by: root <wenjun7j@gmail.com>
|
2026-03-26 14:44:37 -07:00 |
|
|
Qiaolin Yu
|
8c3ccef2d9
|
Fix Kimi K2.5 dp attention+ spec decoding launch crash (#21391)
|
2026-03-26 14:40:26 -07:00 |
|
|
satyamk7054andSatyam Kumar
|
be0cca5596
|
Use torch.addmm instead of separate mm and add_ calls for LoRA torch.native (#20562)
Co-authored-by: Satyam Kumar <satyamk@linkedin.com>
|
2026-03-26 14:35:20 -07:00 |
|
|
satyamk7054andSatyam Kumar
|
e59ea4f6e9
|
fix: torch-native LoRA for multi-adapter case (#20564)
Co-authored-by: Satyam Kumar <satyamk@linkedin.com>
|
2026-03-26 14:34:16 -07:00 |
|
|
Liangsheng Yin
|
fb90c9d298
|
[Test] Consolidate eval accuracy test mixins into eval_accuracy_kit (#21047)
|
2026-03-26 14:26:46 -07:00 |
|
|
Liangsheng Yin
|
e5dd411f64
|
[CI] Add ci-workflow-guide skill and consolidate CI docs (#21429)
|
2026-03-26 13:50:13 -07:00 |
|
|
Liangsheng Yin
|
e5b7650353
|
Fix UnboundLocalError when DetokenizerManager constructor fails (#21471)
|
2026-03-26 13:00:16 -07:00 |
|
|
Liangsheng Yin
|
17f43d1518
|
[CI] Skip stage health check for release branch cut (#21488)
|
2026-03-26 12:54:51 -07:00 |
|
|
Ho-Ren (Jack) Chuang
|
4b5f63e1b8
|
FIX: (NSA) Compute topk_indices_offset when NSA prefill flashmla_sparse is used with FP8 KV cache (#20606)
Signed-off-by: Ho-Ren (Jack) Chuang <horenchuang@bytedance.com>
|
2026-03-26 12:50:50 -07:00 |
|
|
jianzhao-xuandJianzhao Xu
|
3867c6431a
|
Fix bug in dbrx model (#21445)
Co-authored-by: Jianzhao Xu <xujianchao@huawei.com>
|
2026-03-26 11:23:30 -07:00 |
|
|
shuwenn
|
646573e4e8
|
fix: use get_rope_config() to support models without rope_parameters (#21135)
|
2026-03-26 11:22:12 -07:00 |
|
|
McZyWu
|
0906e45cec
|
bugfix for weight loading for qwen3-next (#21313)
|
2026-03-26 21:21:00 +08:00 |
|
|
monkeyLovedingandKelon
|
8febc3650d
|
[NPU] multimodal-gen-test-8-npu-a3,Cache pytorch dependency (#21470)
Co-authored-by: Kelon <kelonlu@163.com>
|
2026-03-26 19:35:34 +08:00 |
|
|
YC Yen-Ching Tseng
|
013fa55630
|
[AMD] CI - fix amd 4-GPU PR test (#21444)
|
2026-03-26 18:16:33 +08:00 |
|
|
Mick
|
238a4b8f8f
|
[diffusion] CI: fix breaking import path in nightly (#21449)
|
2026-03-26 16:33:22 +08:00 |
|
|
Mick
|
35720d9969
|
[diffusion] fix: fix qwen-image with nunchaku (#21415)
|
2026-03-26 16:31:44 +08:00 |
|
|
Anant Sharma
|
f289d173aa
|
[Deps] Bump xgrammar to 0.1.32 (#21032)
|
2026-03-26 01:22:37 -07:00 |
|
|
Chen, ZhentaoandChen, Todd
|
fd535942ac
|
[AMD]Integrate aiter's fused_topk for softmax scoring in topk function (#21421)
Co-authored-by: Chen, Todd <zhenchen@amd.com>
|
2026-03-26 00:57:56 -07:00 |
|
|
R0CKSTAR
|
a305964159
|
[MLX] Add native MLX execution backend for Apple Silicon Mac (#20342)
Signed-off-by: Xiaodong Ye <yeahdongcn@gmail.com>
|
2026-03-26 00:09:17 -07:00 |
|
|
Xiaoyu Zhang
|
7ca015fe65
|
[Diffusion] Refactor diffusion JIT kernel test layout and narrow CI triggers (#21385)
|
2026-03-26 15:02:02 +08:00 |
|
|
Liangsheng Yin
|
79db3bec34
|
[CI] Add PID namespace and ps auxf diagnostics to killall.py (#21401)
|
2026-03-25 23:57:15 -07:00 |
|
|
Liangsheng Yin
|
176c8e7b0e
|
[CI] Simplify CI check actions and add maintenance gate to rerun-ut (#21455)
|
2026-03-25 23:28:18 -07:00 |
|
|
MARATRIX
|
01ccdb91b1
|
[Fix] Add EPLB rebalance support for Kimi K2.5 (#21004)
Signed-off-by: yafeng.li <yafeng.li@mthreads.com>
|
2026-03-25 21:01:40 -07:00 |
|
|
ori
|
f142608408
|
[MUSA] apply_vocab_mask support musa device (#21296)
|
2026-03-25 21:00:58 -07:00 |
|
|
MARATRIXandR0CKSTAR
|
f420b9b4a5
|
[MUSA][Feature] Enable Piecewise CUDA Graph support for MUSA platform (#20758)
Signed-off-by: yafeng.li <yafeng.li@mthreads.com>
Co-authored-by: R0CKSTAR <yeahdongcn@gmail.com>
|
2026-03-25 21:00:28 -07:00 |
|
|
R0CKSTAR
|
abf4f1a47a
|
[MPS] Add StreamContext stub (#20782)
Signed-off-by: Xiaodong Ye <yeahdongcn@gmail.com>
|
2026-03-25 20:59:51 -07:00 |
|
|
R0CKSTAR
|
02521420b3
|
[MPS] Support sglang.check_env (#20753)
Signed-off-by: Xiaodong Ye <yeahdongcn@gmail.com>
|
2026-03-25 20:59:25 -07:00 |
|
|
gjsheuandgengjinsong
|
d9e96153de
|
[NPU] Support Hybrid KV Cache for Ascend backend (#18032)
Co-authored-by: gengjinsong <gengjinsong@huawei.com>
|
2026-03-26 11:27:36 +08:00 |
|
|
Simo Lin
|
b835309f0c
|
Reland: compute M-RoPE positions for preprocessed VL inputs (#21244)
|
2026-03-25 20:12:43 -07:00 |
|
|
DarkSharpness
|
bb29893689
|
[Fix] Try to fix nvcc compilation error (#21246)
|
2026-03-26 10:59:36 +08:00 |
|
|
Aurick Qiao
|
a34e9ed64a
|
Add adjusted_filter_batch (#21260)
|
2026-03-26 10:59:05 +08:00 |
|
|
Aurick Qiao
|
53c1d8e963
|
Fix customized_info offset truncation (#21262)
|
2026-03-26 10:57:51 +08:00 |
|
|
Sam Shleifer
|
1100b9865c
|
Fix MxInt4 MoE returning wrong output variable (#21348)
|
2026-03-26 10:57:09 +08:00 |
|
|
Yanda Cheng
|
662635e7a7
|
fix(sgl-kernel): align wheel METADATA/WHEEL with +cu filename (#21437)
|
2026-03-25 19:44:50 -07:00 |
|
|
MichaelandBingxu Chen
|
80389fec00
|
[AMD] Fix AMD CI: mark /sglang-checkout as git safe.directory in container (#21423)
Co-authored-by: Bingxu Chen <bingxche@amd.com>
|
2026-03-26 10:18:19 +08:00 |
|
|
Xiaoyu Zhang
|
6f2b51ade1
|
[Diffusion] Optimize diffusion Triton rotary embedding by processing multiple heads per token (#21387)
|
2026-03-26 08:59:25 +08:00 |
|