 Khoa Pham
|
d22853480d
|
Fix deterministic inference on models with SWAKVPool (#24395)
|
2026-05-05 20:20:46 +08:00 |
|
|
Bi Xue
|
9fb9a1cca6
|
[sgl] expose swa and mamba cache metrics (#24396)
|
2026-05-05 20:19:50 +08:00 |
|
|
Xiaoyu Zhang
|
67e8bd7a80
|
[codex] Optimize Helios fused norm modulation (#24059)
|
2026-05-05 19:28:37 +08:00 |
|
|
Xiaoyu Zhang
|
8c703f215e
|
Add HunyuanVideo ModelOpt FP8 diffusion support (#23199)
|
2026-05-05 19:27:28 +08:00 |
|
|
billishyahao
|
80ccb6b93c
|
[AMD] fix tbo specv2 seq_lens_cpu NoneType error (#24319)
|
2026-05-05 01:54:43 -07:00 |
|
|
Baizhou ZhangandClaude Opus 4.7
|
e0af36a907
|
[Fix] Fix pypi release workflow (#24417)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-05-05 01:21:06 -07:00 |
|
|
Mick
|
177babcc38
|
[diffusion] optimize: fuse LTX2 split rotary embedding (#24411)
|
2026-05-05 16:07:40 +08:00 |
|
|
YC Yen-Ching Tseng
|
64613543ea
|
[AMD] fix(docker): unbreak nightly when archive.ubuntu.com:80 is unreachable (#24407)
|
2026-05-05 00:39:14 -07:00 |
|
|
|
c2db19ffa4
|
[AMD] Enable EAGLE speculative decoding for Qwen3.5 FP8 and MXFP4 models with aiter's unified attention (#23146)
Co-authored-by: wunhuang <wunhuang@amd.com>
Co-authored-by: sogalin <39478626+sogalin@users.noreply.github.com>
|
2026-05-05 00:09:40 -07:00 |
|
|
Michael
|
244531bc4f
|
[AMD] Add Kimi-K2.6 in nightly tests for MI30x and MI35x (#23848)
|
2026-05-04 23:37:14 -07:00 |
|
|
Yuhao YangandClaude Opus 4.6
|
6279aee716
|
[docs] Update B300 Pro cookbook with accuracy-verified serving configs (#24367)
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
|
2026-05-05 07:26:03 +01:00 |
|
|
Mick
|
04926e1d9f
|
[diffusion] feat: cache encoder results for default negative prompt (#24304)
|
2026-05-05 11:56:01 +08:00 |
|
|
Mick
|
e483e60b72
|
[diffusion] CI: pin diffusion consistency GT revision (#24400)
|
2026-05-05 11:53:22 +08:00 |
|
|
Ethan (Yusheng) SuandCursor
|
2b769d37a4
|
(2/n - prefill optimize)perf(lora): remove GPU-CPU sync barrier (.item()) in MoE LoRA path and remove duplicate code (#24246)
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-05-04 18:11:28 -07:00 |
|
|
Mick
|
2f7d99b7f7
|
[diffusion] cli: support component attention backend overrides (#24320)
|
2026-05-05 08:39:27 +08:00 |
|
|
Xiaoyu ZhangandBBuf Codex
|
078f84d80d
|
[SKILL] Add diffusion benchmark presets for edit and Hunyuan3D models (#24288)
Co-authored-by: BBuf Codex <bbuf-codex@users.noreply.github.com>
|
2026-05-05 08:18:12 +08:00 |
|
|
Ji Zeng
|
4b487ca98b
|
[Fix] NGRAMWorker.update_weights_from_tensor — delegate to target worker (#24344)
|
2026-05-04 16:23:17 -07:00 |
|
|
Liangsheng YinandZhiqiang Xie
|
6a62eabed6
|
consolidate NSA pool construction (#24389)
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
|
2026-05-04 16:04:31 -07:00 |
|
|
Tarushii Goel
|
d7c93e183b
|
[sgl] reduce specdec cpu overhead (#23321)
|
2026-05-04 15:02:03 -07:00 |
|
|
Liangsheng Yinandfzyzcjy
|
4743cf6051
|
misc: add marlin to moe runner choices; drop dead env var doc (#24384)
Co-authored-by: fzyzcjy <ch271828n@outlook.com>
|
2026-05-04 15:01:47 -07:00 |
|
|
Baizhou ZhangandClaude Opus 4.7
|
f059e0264a
|
Fix sgl-deep-gemm release workflow (#24385)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-05-04 14:36:59 -07:00 |
|
|
Lianmin Zheng
|
29dd3a36c0
|
Refactor device timer installation and rename prefill prealloc to bootstrap (#24341)
|
2026-05-04 13:57:13 -07:00 |
|
|
Praneth Paruchuri
|
e93bb638bf
|
[docs]update sm75 to sm80 min gpu support (#24336)
|
2026-05-04 13:50:20 -07:00 |
|
|
Kangyan-ZhouandClaude Opus 4.7
|
0f283a515a
|
[Docker] fix: install nixl stub alongside nixl-cuXX binary (#24369)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-05-04 12:46:38 -07:00 |
|
|
Vladislav Nosivskoy
|
60a1dacd89
|
[HiCache] return cached_tokens_details in sglext for streaming responses (#22055)
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
|
2026-05-04 12:30:17 -07:00 |
|
|
Kangyan-ZhouandClaude Opus 4.7
|
8ffd39e140
|
[CI] Exclude flaky h20 stage from check-stage-health root cause set (#24374)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-05-04 11:41:25 -07:00 |
|
|
Ke Bao
|
6dd7aebb36
|
Minor scheduler fixes (#24359)
|
2026-05-05 02:01:23 +08:00 |
|
|
Sam Shleifer
|
e6f252e9b8
|
Cache FlashInfer autotune configs (#24156)
|
2026-05-05 02:00:40 +08:00 |
|
|
Kangyan-ZhouandClaude Opus 4.7
|
c545a5b1c0
|
[SMG][CI] Add K8s integration tests + wire into pr-test-rust (#24278)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-05-04 10:27:37 -07:00 |
|
|
Yuan Luoandluoyuan.luo
|
e5c58eb9d6
|
[VLM] Optimize Gemma4 VLM with PCG and fuse RMSNorm + residual add + scalar (#24048)
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
|
2026-05-04 09:36:26 -07:00 |
|
|
Mick
|
1be3163011
|
[diffusion] fix: use direct all-to-all for USP collectives (#24366)
|
2026-05-05 00:08:48 +08:00 |
|
|
mispa-msandClaude Opus 4.7
|
62a4df0067
|
[docker] Fix silently-masked cubin download failure; skip prebuilt cubins on aarch64 (#24234)
Signed-off-by: misunp <misunp@nvidia.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-05-04 09:08:01 -07:00 |
|
|
Xiaoyu Zhang
|
4b6d44641b
|
[diffusion] chore: enable channels-last 3D VAE convs by default (#23200)
|
2026-05-04 22:59:31 +08:00 |
|
|
Zhangheng
|
05aed5e1d5
|
[UnifiedRadixTree]: Add KL accuracy CI for UnifiedTree with HiCache (#24346)
|
2026-05-04 20:18:10 +08:00 |
|
|
Liangsheng Yin
|
84f3b44916
|
[tiny] misc cleanups across configs, attention, jit_kernel (#24350)
|
2026-05-04 03:17:14 -07:00 |
|
|
|
952b3caf18
|
feat: use structural tags to enable strict tool calling and reasoning for more models (#21722)
Signed-off-by: Yuchuan <yuchuan.7streams@gmail.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
Co-authored-by: Ubospica <ubospica@gmail.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
|
2026-05-04 02:30:28 -07:00 |
|
|
Khoa Pham
|
ef2b1b6d89
|
Fix flashinfer workspace OOM (#24172)
|
2026-05-04 01:26:35 -07:00 |
|
|
Baizhou ZhangandClaude Opus 4.7
|
de08c804c5
|
Add release workflow for sgl-deep-gemm wheels (#24348)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-05-04 00:58:44 -07:00 |
|
|
|
52b4609789
|
[Docker] Prep for torch 2.11: cu129 fix, image validator, dep cleanup (#23593)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
|
2026-05-04 00:37:55 -07:00 |
|
|
Bingxu ChenandYC Yen-Ching Tseng
|
5eff3c489a
|
[AMD] Deepseek v4 Flash / Pro nightly tests for MI35x ROCm 7.2 (#24203)
Co-authored-by: YC Yen-Ching Tseng <yctseng@amd.com>
|
2026-05-04 00:02:33 -07:00 |
|
|
Ke Bao
|
aea527afdc
|
Fix swa chunk req deferred (#24318)
|
2026-05-04 14:52:15 +08:00 |
|
|
Khoa PhamandClaude Opus 4.7
|
c2d60c3667
|
chore(codeowners): add @kpham-sgl as codeowner for ngram files (#24349)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-05-03 23:27:33 -07:00 |
|
|
Liangsheng Yin
|
a91ae6af9e
|
nextn subclass owns post_load_weights is_nextn (#24333)
|
2026-05-03 22:04:44 -07:00 |
|
|
Liangsheng Yin
|
1dd8f6d5ae
|
dedup state_kv_args setup into helper (#24340)
|
2026-05-03 20:45:26 -07:00 |
|
|
Liangsheng Yin
|
91fa2340ed
|
extract adjust_hybrid_swa_layers_for_pp (#24334)
|
2026-05-03 18:52:54 -07:00 |
|
|
Ethan (Yusheng) Su
|
b7fefc0e85
|
feat(lora): enable csgmv backend with virtual experts for MoE LoRA (#24007)
|
2026-05-03 18:44:17 -07:00 |
|
|
Mick
|
c611a3fb78
|
[diffusion] chore: disable VAE cpu offload by default (#24315)
|
2026-05-04 08:24:51 +08:00 |
|
|
Liangsheng Yin
|
00d620b77d
|
introduce arg_groups/ with nemotron_h hook (#24328)
|
2026-05-03 16:28:11 -07:00 |
|
|
Liangsheng Yin
|
c3b6d20a80
|
Register deepseek_v32 alias instead of rewriting config.json (#24295)
|
2026-05-03 16:02:17 -07:00 |
|
|
Liangsheng Yin
|
53df43d0a3
|
rerun-test: route deepep h200 suite to deepep runner (#24325)
|
2026-05-03 15:57:53 -07:00 |
|