 Wei Zhao
|
90d6d871d6
|
[Attention] Add CuTe DSL backend selection for MLA context prefill (#62069)
Signed-off-by: Wei Zhao <51183510+wzhao18@users.noreply.github.com>
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-10-17 01:21:55 -04:00 |
|
|
Wei ZhaoandCodex
|
be25977532
|
[CI][Tests] Account for FP8 KV-cache rounding in MLA reference (#62067)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-10-16 17:10:08 -07:00 |
|
|
Wei Zhao
|
e365792997
|
[Dependency] Upgrade TokenSpeed MLA to 2.0.3 (#61689)
Signed-off-by: Wei Zhao <51183510+wzhao18@users.noreply.github.com>
|
2026-10-15 22:28:59 -07:00 |
|
|
Wei ZhaoandJee Jee Li
|
4975fda882
|
[Dependency] Upgrade FlashInfer to 0.7.1 (#60948)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-10-14 12:31:08 -07:00 |
|
|
|
8082b62f32
|
[Mooncake] Allow Mamba cache mode none for capacity-only workers (#60712)
Signed-off-by: Wei Zhao <51183510+wzhao18@users.noreply.github.com>
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-13 23:13:58 +00:00 |
|
|
Wei ZhaoandCodex
|
03a7d3776f
|
[Perf] Support minimum KV splits configuration for TokenSpeed MLA decode (#60345)
Signed-off-by: Wei Zhao <51183510+wzhao18@users.noreply.github.com>
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-10-09 23:33:47 +00:00 |
|
|
|
d8fa463e2b
|
[Bugfix][Prefix caching] Fix inconsistent hybrid Mamba prefix cache boundaries (#60533)
Signed-off-by: Wei Zhao <weizha@aws-cmh-slurm-1-login-01.cm.cluster>
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Wei Zhao <weizha@aws-cmh-slurm-1-login-01.cm.cluster>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-10-08 18:33:48 +00:00 |
|
|
Wei Zhaoandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
84bcbc6264
|
[DCP] Enable TokenSpeed MLA with block-interleaved DCP (#59462)
Signed-off-by: Wei Zhao <51183510+wzhao18@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-10-03 17:26:07 +00:00 |
|
|
Wei ZhaoandCodex
|
279012f94d
|
[Docs] Add @wzhao18 to NVIDIA integration and kv offloading code owners (#59456)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Codex <codex@openai.com>
|
2026-09-30 16:12:12 +00:00 |
|
|
Wei Zhao
|
678baf5372
|
[Dependency] Upgrade FlashInfer to 0.7.0.post1 (#59323)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-09-30 02:34:36 +00:00 |
|
|
|
44bf011f44
|
[Dependency] Upgrade FlashInfer version to 0.7.0 (#58069)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
|
2026-09-23 22:45:23 -07:00 |
|
|
Wei Zhao
|
ccde9c61e9
|
[Bugfix] Restore KV cache metadata GET method for external event consumer (#56925)
Signed-off-by: Wei Zhao <51183510+wzhao18@users.noreply.github.com>
|
2026-09-17 23:01:35 +00:00 |
|
|
Wei Zhao
|
f30a195bbb
|
[Bugfix] Fix incorrect Mamba block allocation estimate that prevents request admission (#57050)
Signed-off-by: Wei Zhao <51183510+wzhao18@users.noreply.github.com>
|
2026-09-16 07:23:20 +00:00 |
|
|
Wei Zhao
|
9d88ceb026
|
[KDA] Update flashKDA to support bf16 checkpoint state (#56485)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-09-11 23:53:24 +00:00 |
|
|
|
7cdd9304ae
|
[KV Connector] Support symmetric DCP disagg for hybrid mamba models (#55531)
Signed-off-by: Wei Zhao <weizha@oci-aga-slurm-1-vscode-02.cm.cluster>
Signed-off-by: Wei Zhao <51183510+wzhao18@users.noreply.github.com>
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Wei Zhao <weizha@oci-aga-slurm-1-vscode-02.cm.cluster>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-09-10 11:12:15 -07:00 |
|
|
Wei ZhaoandOpenAI Codex
|
8c87c333b8
|
[Perf] Fix TRTLLM ragged prefill perf regression (#55499)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-09-09 20:38:20 +00:00 |
|
|
Wei Zhao
|
a69402aaa8
|
[Perf] Integrate FlashInfer KDA kernels (#55364)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-09-07 20:29:30 -07:00 |
|
|
Wei Zhao
|
6748217fb9
|
[Bugfix] Fix Kimi K3 NVFP4 MoE weight conversion OOM (#55407)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-09-07 11:45:25 +08:00 |
|
|
Wei Zhao
|
c3ec0d29f5
|
[Bugfix] Fix cuda profiler missing bug (#55237)
|
2026-09-07 03:15:57 +00:00 |
|
|
Wei ZhaoandOpenAI Codex
|
16328c7a77
|
[Perf] Kimi K3 nvfp4 Align in_proj weights by 128 to avoid elementwise copy (#55242)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-09-05 10:46:47 +08:00 |
|
|
|
7ab2923489
|
[Flashinfer] Upgrade Flashinfer version to 0.6.18 (#54313)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Signed-off-by: Wei Zhao <51183510+wzhao18@users.noreply.github.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com>
|
2026-08-30 16:01:05 -07:00 |
|
|
Wei ZhaoandYifan Qiao
|
7fd9cc036e
|
[KV Connector] Support MooncakeStore with hybrid DCP prefix caching (#53324)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Signed-off-by: wzhao18 <weizha@nvidia.com>
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
|
2026-08-29 02:10:23 +00:00 |
|
|
Wei Zhao
|
94d96e2446
|
[Bugfix] Release CUDA graph profiling memory before KV cache allocation (#53955)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-08-27 01:35:59 +00:00 |
|
|
Wei ZhaoandOpenAI Codex
|
f8e0602713
|
Support kimi k3 nvfp4 checkpoint (#53132)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-21 05:59:44 +00:00 |
|
|
Wei Zhao
|
689be2bcd3
|
Upgrade Flashinfer version to 0.6.17 (#52681)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-08-18 23:04:36 +08:00 |
|
|
Wei Zhao
|
d1e3eee6fb
|
[Spec decode] Support Kimi-K3 DCP with DSpark (#52188)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-08-17 13:08:45 -07:00 |
|
|
Wei Zhao
|
608c12473f
|
[Attention] Fix MLA prefill workspace allocation size (#51733)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-08-11 05:34:30 +00:00 |
|
|
|
f18e10a7e1
|
Bump Flashinfer version to 0.6.16.post3 (#50892)
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
|
2026-08-09 00:54:07 -07:00 |
|
|
|
61a09532f2
|
Bump Flashinfer version to 0.6.15 (#48914)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Signed-off-by: Wei Zhao <weizha@oci-aga-slurm-1-vscode-02.cm.cluster>
Co-authored-by: Wei Zhao <weizha@oci-aga-slurm-1-vscode-02.cm.cluster>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2026-07-22 13:32:05 -07:00 |
|
|
Wei ZhaoandYongye Zhu
|
2afa3f7e95
|
[Perf] Minimax M3 - Support cross-layer allreduce-norm fusion (#47631)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
|
2026-07-07 21:16:32 -07:00 |
|
|
Wei Zhao
|
b153dd3f28
|
[Bugfix] Use larger workspace size for Flashinfer MLA LSE (#47074)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-06-29 22:11:03 -07:00 |
|
|
Wei ZhaoandJee Jee Li
|
4708292d48
|
Bump flashinfer version to 0.6.13 (#46683)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-06-29 09:30:57 -07:00 |
|
|
Wei Zhao
|
95528527ea
|
[Bugfix][Mooncake] Fix Mooncake lookup prefixes with DCP > 1 (#46855)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-06-28 14:36:23 -07:00 |
|
|
Wei ZhaoandYifan Qiao
|
d20dbf921b
|
[Mooncake] Only check and store new KV cache range (#46412)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
|
2026-06-24 03:10:50 -07:00 |
|
|
Wei Zhao
|
05a0caba91
|
[Mooncake] Optimize lookup pool key string construction (#46188)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-06-24 11:51:53 +08:00 |
|
|
Wei Zhao
|
5fd3b276f8
|
[Mooncake] Skip KV lookup for non-reachable SWA blocks (#45444)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-06-18 02:23:20 -07:00 |
|
|
Wei ZhaoandYifan Qiao
|
a6183563b6
|
[Prefix Caching] DeepSeekv4 - Support selective prefix-cache retention for sliding-window KV cache (#43447)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>
|
2026-06-04 00:48:31 -07:00 |
|
|
Wei Zhaoandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
ace95c9cf8
|
[Bugfix] Update TrtLLM MoE routing methods (#44347)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-03 02:56:43 -07:00 |
|
|
Wei Zhao
|
969aec4bc8
|
[Bugfix] Fix Deepseek v4 non-mega-moe model init error (#44356)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-06-02 18:26:30 -07:00 |
|
|
Wei ZhaoandWei Zhao
|
2427094152
|
[Feature] Support EPLB for DeepSeek v4 Mega Moe (#43339)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Wei Zhao (Engrg-Hardware 1) <weizha@login-lyris01.lyris.clusters.nvidia.com>
|
2026-06-02 10:56:44 -07:00 |
|
|
Wei Zhao
|
f2caefe226
|
[UX] Increase DP Coordinator startup timeout from 30s to 120s (#42343)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-05-28 03:31:45 -07:00 |
|
|
Wei Zhaoandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
9aaf83ef50
|
[CI failure] Temporarily disable using persistent cache for flashinfer autotune (#43119)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Signed-off-by: Wei Zhao <51183510+wzhao18@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
2026-05-19 11:44:32 -07:00 |
|
|
Wei Zhao
|
8c296de63b
|
[Perf] Re-enable flashinfer autotune by default and cleanup (#42857)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-05-18 09:12:27 -07:00 |
|
|
Wei Zhao
|
986edc858a
|
[Bugfix] Fix DeepSeek v4 topk numerical issue for unaligned max-model-len (#42169)
|
2026-05-09 20:30:08 -07:00 |
|
|
Wei Zhao
|
c51df43005
|
Disable flashinfer autotune temporarily due to correctness issues (#41524)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-05-03 16:19:59 +00:00 |
|
|
Wei Zhao
|
0ff1bf9bb1
|
[Bugfix] Fix failure to allocate KV blocks error (#41282)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-04-29 18:44:07 -07:00 |
|
|
Wei ZhaoandWei Zhao
|
8b49cf3a37
|
[Bugfix] Fix max_num_batched_token not captured in cuda graph (#40734)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Signed-off-by: Wei Zhao <51183510+wzhao18@users.noreply.github.com>
Co-authored-by: Wei Zhao (Engrg-Hardware 1) <weizha@login-bia02.bia.clusters.nvidia.com>
|
2026-04-28 21:33:06 -07:00 |
|
|
Wei Zhao
|
803b9d7881
|
[Bugfix] Fix Deepseek V4 import error due to AOT compile cache loading (#41090)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Signed-off-by: Wei Zhao <51183510+wzhao18@users.noreply.github.com>
|
2026-04-28 21:08:16 -07:00 |
|
|
|
c8bbe05189
|
[Perf] Update TRTLLM supported MoE routing methods (#39141)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Signed-off-by: Wei Zhao <51183510+wzhao18@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: root <root@bia0030.bia.clusters.nvidia.com>
Co-authored-by: root <root@bia0036.bia.clusters.nvidia.com>
|
2026-04-27 14:16:22 -04:00 |
|
|
Wei Zhao
|
59b2f7b640
|
[Perf] Fuse Zero Initializer for FP8 DeepGemm Block Quant Kernel (#39547)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-04-11 07:16:51 -07:00 |
|
|
Wei ZhaoandJee Jee Li
|
92fbec391b
|
[Bug] Fix routing bias dtype for trtllm per-block fp8 moe (#38989)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-04-08 19:42:43 -07:00 |
|
|
Wei Zhao
|
0be9516ea4
|
[Bug] Fix Trtllm Fp8 MoE Weight Shuffle Memory Fragamentation (#39054)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-04-07 08:04:08 -04:00 |
|
|
Wei ZhaoandRobert Shaw
|
1af6f78ae5
|
[Perf] Change Trtllm fp8 MoE to use Shuffled Weights and BlockMajorK Layout (#38993)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
|
2026-04-05 10:54:31 -04:00 |
|
|
Wei Zhao
|
b69bf2f0b1
|
[Perf] Use torch compile to fuse pack topk in trtllm moe (#37695)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Signed-off-by: Wei Zhao <51183510+wzhao18@users.noreply.github.com>
|
2026-03-27 17:30:46 -06:00 |
|
|
Wei Zhaoandroot
|
0904b6550d
|
Fix multi-node allreduce fusion (#38136)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: root <root@theia0053.lyris.clusters.nvidia.com>
|
2026-03-26 20:24:36 +00:00 |
|
|
Wei Zhao
|
74056039b7
|
Fix minimax m2.5 nvfp4 kv scales weight loading (#37214)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-03-26 00:48:06 +00:00 |
|
|
|
0140eafb15
|
[Bug] Fix FlashInfer allreduce fusion workspace uninitialized error (#37461)
Signed-off-by: root <root@prenyx0169.a51.clusters.nvidia.com>
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Signed-off-by: <>
Co-authored-by: root <root@prenyx0169.a51.clusters.nvidia.com>
Co-authored-by: root <root@prenyx0042.a51.clusters.nvidia.com>
|
2026-03-20 03:09:21 -04:00 |
|
|
Wei Zhao
|
e27b8ba3d1
|
[Bug] Fix fp8 trtllm MoE modular kernel supported routing methods (#37346)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-03-19 11:43:06 -04:00 |
|
|
Wei Zhao
|
b36adfa349
|
[Perf] Set Flashinfer sparse MLA as default backend for FP8 kv cache (#37252)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-03-17 20:09:20 +00:00 |
|
|
Wei Zhao
|
a3a51d20e7
|
[Benchmark] Improvements to attention benchmark script (#37115)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-03-16 22:22:40 +00:00 |
|
|
Wei ZhaoandMichael Goin
|
2e693f48e7
|
[Perf] Add TRTLLM FP8 MoE Modular Kernel (#36307)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2026-03-12 07:32:31 -07:00 |
|
|
Wei ZhaoandRobert Shaw
|
84e436ed1c
|
[Bug] Fix TRTLLM Block FP8 MoE Monolithic (#36296)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
|
2026-03-10 22:04:47 -04:00 |
|
|
Wei Zhao
|
379689d533
|
[Perf] Support FP8 KV cache for Flashinfer MLA Sparse (#35891)
|
2026-03-07 13:51:54 -08:00 |
|
|
Wei ZhaoandCyrus Leung
|
ea5f903f80
|
Bump Flashinfer Version and Re-enable DeepSeek NVFP4 AR+Norm Fusion (#34899)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
|
2026-02-20 13:37:31 -08:00 |
|
|
Wei Zhao
|
f24b2de3d3
|
[Test] Add FP8 KV Cache Testing for MLA Backends (#34473)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-02-20 18:51:58 +00:00 |
|
|
Wei Zhao
|
7f51e93864
|
[Bug] Fix DeepSeek V3 weight loading caused by incorrect prefix (#34876)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-02-18 23:20:30 -08:00 |
|
|
Wei Zhao
|
b37b679770
|
[Feature][Perf] Support Selective CPU Weight Offloading (#34535)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-02-13 20:02:24 -08:00 |
|
|
Wei ZhaoandMichael Goin
|
59d53066d8
|
[Feature] Support CPU Offloading without Pytorch Pinned Memory that leads to doubled allocation (#32993)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
|
2026-02-13 08:11:26 -08:00 |
|
|
Wei Zhao
|
5aff2699bd
|
Fix CI failure - Flashinfer Kernel tests (#34316)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-02-11 14:17:16 -08:00 |
|
|
Wei Zhao
|
91a07ff618
|
[Bugfix] Fix DeepSeek v3.2 tokenizer outputting None issue (#33832)
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
|
2026-02-05 23:50:49 +00:00 |
|