 Baizhou Zhang
|
2fca6d69aa
|
bumping sgl-deep-gemm to 0.2.0 (#39371)
|
2026-09-14 15:30:31 -07:00 |
|
|
Baizhou ZhangandChunan Zeng
|
5ebb16005d
|
[DeepSeek-V4.1] Bump FlashMLA to the fork's rebase head (v4.1 kernels) (#39171)
Co-authored-by: Chunan Zeng <zcnrex@gmail.com>
|
2026-09-13 15:43:19 -07:00 |
|
|
Baizhou Zhang
|
7763f666f3
|
Fix DeepGEMM release MegaMoE validation without RDMA (#39245)
|
2026-09-12 20:27:29 -07:00 |
|
|
Baizhou Zhang
|
a8b5616303
|
Fix DeepGEMM release dependencies and bound GPU validation (#39241)
|
2026-09-12 17:00:58 -07:00 |
|
|
|
a66451c058
|
[GLM-5.3 Flash] Restore and enable KPool metadata fusion (#38845)
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: zRzRzRzRzRzRzR <Yuxuan.Zhang2@liverpool.ac.uk>
Co-authored-by: Shijin Zhang <75300765+Dovis01@users.noreply.github.com>
Co-authored-by: zanes-ops <zanes@nvidia.com>
|
2026-09-12 16:01:11 -07:00 |
|
|
Baizhou Zhang
|
56a4f47ca6
|
[CI] Fix base-a wait for skipped CPU matrix (#39195)
|
2026-09-11 23:39:53 -07:00 |
|
|
Baizhou Zhang
|
3bb2a5231a
|
[CI] Extend DeepGEMM SM90 test timeout to four hours (#39194)
|
2026-09-11 23:36:54 -07:00 |
|
|
Baizhou Zhang
|
9c365e97b1
|
[CI] Fix DeepGEMM sanitizer setup and Blackwell test timeouts (#39163)
|
2026-09-11 20:54:52 -07:00 |
|
|
Baizhou Zhang
|
29cc9d2dc9
|
[CI] Install elfutils headers for DeepGEMM wheel builds (#39152)
|
2026-09-11 17:29:40 -07:00 |
|
|
Baizhou Zhang
|
fa6e657b93
|
[misc] Update CI permission (#38834)
|
2026-09-10 01:38:58 -07:00 |
|
|
Baizhou Zhang
|
e54ff1efb9
|
[CP V1 Deprecation 5/5] Update prefill CP documentation (#36230)
|
2026-09-08 19:27:49 -07:00 |
|
|
Baizhou Zhang
|
ed183d45ac
|
[CP V1 Deprecation 4/5] Canonicalize prefill CP API names (#36229)
|
2026-09-08 16:03:36 -07:00 |
|
|
Baizhou Zhang
|
85d39401c8
|
[CP V1 Deprecation 3.5/5] Deprecate HIP/NPU/MUSA prefill CP and remove legacy implementation (#38293)
|
2026-09-07 15:39:34 -07:00 |
|
|
Baizhou Zhang
|
503e36cbae
|
Tiny Update CI Permission (#38278)
|
2026-09-06 22:17:48 -07:00 |
|
|
Baizhou Zhang
|
b6c31b155c
|
[CP V1 Deprecation 3/5] Remove generic prefill CP v1 runtime (#36228)
|
2026-09-06 21:53:53 -07:00 |
|
|
Baizhou Zhang
|
ff1285cc28
|
[CP V1 Deprecation 2/5] Make strategy prefill CP canonical (#36223)
|
2026-09-03 20:24:19 -07:00 |
|
|
Baizhou Zhang
|
fd70325c10
|
[CI] Add dspark + dsv4 e2e test (#37665)
|
2026-09-03 14:26:25 -07:00 |
|
|
Baizhou Zhang
|
07c8f7294d
|
Bump sgl-deep-gemm to 0.1.7 (#37279)
|
2026-08-31 17:16:34 -07:00 |
|
|
Baizhou Zhang
|
a7ee399904
|
Bump sgl-deep-gemm to v0.1.6 (#36998)
|
2026-08-29 19:51:02 -07:00 |
|
|
Baizhou Zhang
|
46334460a6
|
[CI] Temporarily disable GB300 jobs (#36981)
|
2026-08-28 23:56:54 -07:00 |
|
|
|
395c2258c3
|
[Docs] Add GLM-5.3 cookbook (#36827)
Co-authored-by: JustinTong0323 <xinyuantong.cs@gmail.com>
Co-authored-by: Zijie Xia <zijie.xia@radixark.ai>
Co-authored-by: Mohammad Angkad <176301910+mmangkad@users.noreply.github.com>
|
2026-08-28 14:56:06 +00:00 |
|
|
Baizhou Zhang
|
76217f6603
|
Revert "[NPU] [bugfix] Fix import of ggml_moe_a8_vec and Fix NPU MLA HiCache backup accessing missing data_ptrs" (#36747)
|
2026-08-27 16:16:30 -07:00 |
|
|
Baizhou ZhangandRyan Stewart
|
41e7612dee
|
[Model] Support Nemotron 3.5 Lightning speculative decoding (#36186)
Co-authored-by: Ryan Stewart <rystewart@nvidia.com>
|
2026-08-25 16:43:58 -07:00 |
|
|
Baizhou Zhang
|
2d88c79b3e
|
[CI] Add Kimi-K3 MMMU-Pro accuracy coverage (#36284)
|
2026-08-25 16:33:46 -07:00 |
|
|
Baizhou Zhang
|
833be86c15
|
[CP V1 Deprecation 1/5] Migrate tests to strategy-based prefill CP (#36222)
|
2026-08-24 20:15:34 -07:00 |
|
|
Baizhou Zhang
|
3b5909de0e
|
[DeepSeek V4] Add W4A4 MegaMoE server flag (#35918)
|
2026-08-21 18:44:18 -07:00 |
|
|
Baizhou Zhang
|
60ff1e33a5
|
[DeepSeek V4] Default FP4 checkpoints to FlashInfer MXFP4 MoE (#35919)
|
2026-08-21 16:48:58 -07:00 |
|
|
Baizhou Zhang
|
92eeed41d7
|
[Docker] Defer CUDA 13 NCCL override until after dependency resolution (#35756)
|
2026-08-20 14:48:07 -07:00 |
|
|
Baizhou Zhang
|
d287880a7a
|
Update deepep for SBO feature (#35450)
|
2026-08-19 23:37:13 -07:00 |
|
|
Baizhou Zhang
|
cfc6dfb364
|
Apply latest DeepEP branch (#34923)
|
2026-08-18 16:24:50 -07:00 |
|
|
Baizhou Zhang
|
b814a7e812
|
[CI] Skip fast-fail for scheduled stages (#35392)
|
2026-08-18 15:07:33 -07:00 |
|
|
Baizhou Zhang
|
5b60b7c651
|
[DSV4] Turn on mhc post pre fusion by default (#35214)
|
2026-08-18 00:03:37 -07:00 |
|
|
Baizhou Zhang
|
53621818e4
|
[Docs] Enable PD disaggregation for DSV4 low-latency recipes (#35224)
|
2026-08-17 20:07:27 -07:00 |
|
|
Baizhou Zhang
|
c2c1c4d3eb
|
[CI] Move DSA PD+MTP+CP Layersplit test to basic B300 test suite (#35220)
|
2026-08-17 17:44:31 -07:00 |
|
|
Baizhou Zhang
|
bc312d185d
|
Clean deprecated DeepSeek V4 Environs (#34926)
|
2026-08-17 16:07:00 -07:00 |
|
|
Baizhou Zhang
|
e161bd1265
|
Fix Python packaging shadowing in DeepEP wheel builds (#34937)
|
2026-08-15 03:27:32 -07:00 |
|
|
Baizhou Zhang
|
8d44091326
|
Update sgl-deep-ep release workflow for DeepEP v2 (#34914)
|
2026-08-15 02:08:28 -07:00 |
|
|
Baizhou Zhang
|
7769f54feb
|
[Kimi-K3] Use explicit SiTU activation for MegaMoE (#34883)
|
2026-08-15 01:41:59 -07:00 |
|
|
Baizhou Zhang
|
a1844709f1
|
[CI] Trim Qwen3.5 FP8 GB300 performance batches (#34882)
|
2026-08-14 16:45:11 -07:00 |
|
|
Baizhou Zhang
|
8b4faa3336
|
[Docs] Update Kimi-K3 installation options (#34886)
|
2026-08-14 16:19:23 -07:00 |
|
|
Baizhou Zhang
|
0a6bbbe128
|
[Fix] Restore layer-level DSV4 RoPE policy (#34788)
|
2026-08-13 21:26:45 -07:00 |
|
|
Baizhou Zhang
|
9c0d4cba3f
|
[CI] Split Kimi K2.5 performance batches by config (#34669)
|
2026-08-13 03:20:50 -07:00 |
|
|
Baizhou Zhang
|
273d978bed
|
[CI] Use default installer for B300 tests (#34635)
|
2026-08-12 16:21:40 -07:00 |
|
|
Baizhou Zhang
|
983dfd6a9a
|
[Misc] Sanitize the structure of environ.py (#34472)
|
2026-08-11 16:31:33 -07:00 |
|
|
Baizhou Zhang
|
b498f46271
|
[CI] Add MegaMoE runner compatibility alias (#34326)
|
2026-08-10 19:47:38 -07:00 |
|
|
Baizhou Zhang
|
a92bbf2f24
|
docs: remove DSV4 low-latency chunked prefill size (#34333)
|
2026-08-10 17:23:43 -07:00 |
|
|
Baizhou Zhang
|
56e8bb49b8
|
fix(ci): constrain NeMo Skills evaluator dependencies (#34322)
|
2026-08-10 16:56:46 -07:00 |
|
|
Baizhou Zhang
|
c9444deef4
|
Docker: install DeepEP from release wheels (#34041)
|
2026-08-07 23:51:09 -07:00 |
|
|
Baizhou Zhang
|
eb3cc879e0
|
Install DeepEP from release wheels (#33932)
|
2026-08-07 15:38:44 -07:00 |
|
|
Baizhou Zhang
|
8fc66d1a62
|
docker: pin Kimi images to SGLang commit (#34030)
|
2026-08-07 14:49:26 -07:00 |
|
|
Baizhou Zhang
|
8a22b8305d
|
docker: add Kimi K3 artifacts and build hpc-ops with C++20 (#33956)
|
2026-08-07 13:50:44 -07:00 |
|
|
Baizhou Zhang
|
5e60363960
|
Fix prefill CP graph overflow with larger bucket search (#33906)
|
2026-08-07 01:33:14 -07:00 |
|
|
Baizhou Zhang
|
e0af47b03e
|
Fix sgl-deep-ep builder dependencies (#33866)
|
2026-08-06 16:30:02 -07:00 |
|
|
Baizhou Zhang
|
ba9074035a
|
Build and release sgl-deep-ep wheels (#33498)
|
2026-08-06 02:07:36 -07:00 |
|
|
Baizhou Zhang
|
0e584529f5
|
[CI] Remove profiling from nightly tests (#33832)
|
2026-08-06 01:16:08 -07:00 |
|
|
Baizhou Zhang
|
5d1a0c7129
|
Revert "Warn on risky serving-time Triton work" (#33826)
|
2026-08-05 23:36:10 -07:00 |
|
|
Baizhou Zhang
|
f9b954ddb1
|
[CI] Temporarily disable prefill cuda graph for qwen3.5 nightly test (#33772)
|
2026-08-05 18:52:57 -07:00 |
|
|
Baizhou Zhang
|
070fde72bf
|
[CI] Remove some unneeded CP tests (#33763)
|
2026-08-05 16:07:14 -07:00 |
|
|
Baizhou Zhang
|
25035bff8d
|
Use main branch in Kimi Dockerfiles (#33760)
|
2026-08-05 15:33:14 -07:00 |
|
|
Baizhou Zhang
|
87ed82ff7e
|
Remove custom all-reduce disable from Kimi-K3 B300 recipe (#33612)
|
2026-08-04 16:07:31 -07:00 |
|
|
Baizhou Zhang
|
6808c6d571
|
[Tiny] Little enhancement of Kimi-K3 test (#33609)
|
2026-08-04 15:36:41 -07:00 |
|
|
Baizhou Zhang
|
eb31a53338
|
Revert "Add flashinfer rmsnorm + quant fusion support SM90, SM100, SM120" (#33455)
|
2026-08-03 19:03:56 -07:00 |
|
|
Baizhou Zhang
|
7f6a2e2b50
|
[Refactor] Clean up and split DSA indexer (#33443)
|
2026-08-03 18:05:01 -07:00 |
|
|
Baizhou Zhang
|
0bf0640b9d
|
[CP] Support breakable CUDA graphs for zigzag strategy (#33136)
|
2026-08-02 23:11:57 -07:00 |
|
|
Baizhou Zhang
|
e824b24250
|
[CP] Fuse zigzag attention into a single call (#33137)
|
2026-08-02 20:46:42 -07:00 |
|
|
Baizhou Zhang
|
e1964da451
|
[Docs] Add RTX 5090 DeepSeek-V4 recipe (#33157)
|
2026-07-31 19:04:23 -07:00 |
|
|
Baizhou Zhang
|
fd28242b68
|
[CI] Pin NCCL ports for GB300 PR tests (#33044)
|
2026-07-31 02:28:37 -07:00 |
|
|
Baizhou Zhang
|
d12ea3e9ba
|
docker: add Kimi K3 images (#32760)
|
2026-07-29 03:02:28 -07:00 |
|
|
|
ef6c07008b
|
Support DCP for Kimi Linear model (#32612)
Co-authored-by: Julien Lin <jullin@nvidia.com>
Co-authored-by: kpham-sgl <khoa.pham@radixark.ai>
|
2026-07-28 22:59:58 -07:00 |
|
|
Baizhou Zhang
|
b21cc8eb9b
|
[misc] Update CodeOwner (#32717)
|
2026-07-28 19:55:14 -07:00 |
|
|
Baizhou Zhang
|
082b2a10b6
|
Add local ZIP uploader for whl releases (#32489)
|
2026-07-27 00:03:59 -07:00 |
|
|
Baizhou Zhang
|
f15b43242b
|
Bump sgl-deep-gemm to 0.1.5 (#32345)
|
2026-07-24 14:03:38 -07:00 |
|
|
Baizhou Zhang
|
3d0c6bf57f
|
[Fix] Fix trtllm_mla backend + fp8 kv cache without rope (#32181)
|
2026-07-23 14:55:18 -07:00 |
|
|
Baizhou Zhang
|
ed26a111b2
|
Revert "docker: install dynamo nightly in the dev image for rapid iteration/testing" (#32257)
|
2026-07-23 14:51:43 -07:00 |
|
|
Baizhou Zhang
|
20f6a416e7
|
[Tiny] Skip sm120 deepgemm test temporarily (#32193)
|
2026-07-23 02:54:58 -07:00 |
|
|
Baizhou Zhang
|
5387e23ecd
|
[Tiny]Correct runner for testing deepgemm (#32174)
|
2026-07-23 01:13:14 -07:00 |
|
|
Baizhou Zhang
|
fc0cbb795d
|
[Misc] Add sm120 tests to DeepGemm release pipeline (#31841)
|
2026-07-21 22:19:23 -07:00 |
|
|
Baizhou Zhang
|
9668d9ea72
|
Support GPT-OSS zigzag CP with TRTLLM-MHA (#31732)
|
2026-07-20 00:48:04 -07:00 |
|
|
Baizhou Zhang
|
7a03d30149
|
Support MiMo V2.5 with zigzag context parallelism (#29972)
|
2026-07-19 02:36:40 -07:00 |
|
|
Baizhou Zhang
|
38b29dcd6c
|
Fix SM120 NVFP4 KV cache test OOM (#31653)
|
2026-07-18 00:53:47 -07:00 |
|
|
Baizhou Zhang
|
304a529558
|
Revert "Bump FlashInfer to 0.6.15 and revert regressions" (#31625)
|
2026-07-17 16:46:33 -07:00 |
|
|
Baizhou Zhang
|
eaeb779ea4
|
[Doc] Update GLM5.2 Cookbook with LayerSplit usage (#31577)
|
2026-07-17 02:25:50 -07:00 |
|
|
Baizhou Zhang
|
e835512303
|
Add nightly test for GLM5.2 LayerSplit (#31512)
|
2026-07-17 00:29:14 -07:00 |
|
|
Baizhou Zhang
|
82e7cdcff9
|
[Misc] Remove a few dead code paths in DSA (#30973)
|
2026-07-12 23:25:03 -07:00 |
|
|
Baizhou Zhang
|
e1d51be91f
|
[Tiny] Fix a typo in cookbook (#30837)
|
2026-07-10 21:47:35 -07:00 |
|
|
Baizhou Zhang
|
07165d5daa
|
Add DCP to runtime parallel context (#30478)
|
2026-07-10 21:23:41 -07:00 |
|
|
Baizhou Zhang
|
e8646701c1
|
Update GLM-5.2 NVFP4 cookbook (#30826)
|
2026-07-10 15:56:32 -07:00 |
|
|
Baizhou Zhang
|
3f1694f5e0
|
Update sgl-deep-gemm to 0.1.4.post1 (#30697)
|
2026-07-10 13:30:43 -07:00 |
|
|
|
2c6cd1ef41
|
[Dep] Upgrade flashinfer to 0.6.14 (#29910)
Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>
Co-authored-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
|
2026-07-09 17:52:33 -07:00 |
|
|
Baizhou Zhang
|
7e936f690e
|
[Tiny] Fix Lint in #30645 (#30699)
|
2026-07-09 15:30:48 -07:00 |
|
|
Baizhou Zhang
|
2b3d9ad375
|
[Tiny] Fix docstring in CP abstractions (#30579)
|
2026-07-08 18:41:40 -07:00 |
|
|
Baizhou Zhang
|
fa278a762c
|
Fix FA3 prefill CP NaNs (#30439)
|
2026-07-07 20:16:09 -07:00 |
|
|
Baizhou Zhang
|
946804e042
|
Disable FA3 sparse mask kernels by default (#30356)
|
2026-07-07 01:46:44 -07:00 |
|
|
Baizhou Zhang
|
5eb1b6a7ba
|
Remove retired DSA env paths (#29912)
|
2026-07-05 22:58:02 -07:00 |
|
|
Baizhou Zhang
|
e552f6ed75
|
[Fix] Fix DSA indexer fusion for NeoX RoPE (#30111)
|
2026-07-04 03:20:55 -07:00 |
|
|
Baizhou Zhang
|
1f0f353d92
|
[CI] Add GLM52 NVFP4 MTP B200 tests (#30021)
|
2026-07-03 13:43:38 -07:00 |
|
|
Baizhou Zhang
|
e3258d3b54
|
[Fix] Turn off dsa indexer fusion by default (#30018)
|
2026-07-03 01:08:06 -07:00 |
|
|
Baizhou Zhang
|
c312cdd3a7
|
Upgrading tvm-ffi/sgl-deep-gemm/tilelang (#29554)
|
2026-07-01 12:32:18 -07:00 |
|
|
Baizhou Zhang
|
677a11bfa9
|
[Doc] Tiny update dsv4 doc (#29827)
|
2026-07-01 01:47:35 -07:00 |
|
|
Baizhou Zhang
|
cc238270b1
|
Update GLM tests to 5.2 and delete redundant tests (#29686)
|
2026-06-29 23:04:26 -07:00 |
|