 Canlin GuoandClaude Opus 5.5
|
fe4df3df0e
|
[Bugfix][GLM-5.3-Flash] Restore MTP index sharing across draft iterations (#61079)
Signed-off-by: Canlin <canlinguosdu@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
2026-10-12 05:41:52 +00:00 |
|
|
|
ad73a4740d
|
[Perf][DSv4.1] Trim the last KV-source layer in decoder replay (#59894)
Signed-off-by: Canlin <canlinguosdu@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Juntian Liu <Juntianl777@gmail.com>
|
2026-10-09 06:07:49 +00:00 |
|
|
|
f92b78f6ef
|
[Kernel][DSV4.1] Fuse MXFP8 wo_b GEMM with sequence-parallel reduce-scatter (#57428)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
Signed-off-by: Canlin <canlinguosdu@gmail.com>
Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-09-22 01:07:17 -07:00 |
|
|
|
08633cb5cd
|
[Qwen3.8-Flash-Next] Enable FP8 TP with FlashInfer TRTLLM MoE (#55867)
Signed-off-by: Canlin <canlinguosdu@gmail.com>
Signed-off-by: Isotr0py <Isotr0py@outlook.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: Isotr0py <Isotr0py@outlook.com>
|
2026-09-17 08:56:28 +00:00 |
|
|
Canlin GuoandCodex
|
03f67b3ad1
|
[Perf][DSV4.1] Pad shared experts for native MegaMoE fusion (#56568)
Signed-off-by: Canlin <canlinguosdu@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-09-16 17:08:42 +08:00 |
|
|
|
3f55ad2f07
|
[Qwen3.8-Flash-Next] Fuse PLE residual and QSA output gate (#55309)
Signed-off-by: Canlin <canlinguosdu@gmail.com>
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Kimi Code <noreply@moonshot.cn>
|
2026-09-14 12:16:25 +00:00 |
|
|
Canlin GuoandCodex
|
dca96bf97b
|
[Bugfix][Spec Decode] Avoid fastsafetensors deadlock for PP draft models (#54416)
Signed-off-by: Canlin <canlinguosdu@gmail.com>
Co-authored-by: Codex <noreply@openai.com>
|
2026-09-12 14:22:30 +08:00 |
|
|
Canlin GuoandOpenAI Codex
|
8e1f97e709
|
[Qwen3.8-Flash-Next] Tune FP8 TP2/TP4 Triton MoE on B200 (#55890)
Signed-off-by: Canlin <canlinguosdu@gmail.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-09-08 22:45:18 +08:00 |
|
|
Canlin Guo
|
fd4a151262
|
[Kernel] Reuse Qwen4Exp HC combine-norm for MTP input (#54687)
Signed-off-by: Canlin Guo <canlinguosdu@gmail.com>
Signed-off-by: Canlin <canlinguosdu@gmail.com>
|
2026-09-04 02:57:56 -07:00 |
|
|
Canlin Guoandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
b383e16396
|
[Bugfix] Reset cached Mamba align metadata on profiling teardown (#54044)
Signed-off-by: Canlin Guo <canlinguosdu@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-30 00:43:20 -07:00 |
|
|
Canlin Guo
|
aa640684cc
|
[Kimi K3][Kernel] Support DS conv-state layout in fused KDA decode kernel (#53396)
Signed-off-by: Canlin Guo <canlinguosdu@gmail.com>
|
2026-08-26 23:54:50 -07:00 |
|
|
Canlin Guo
|
bc2d63e650
|
[Kimi K3][Kernel] Enable low-latency decode GEMM dispatch on SM100 (#53534)
Signed-off-by: Canlin Guo <canlinguosdu@gmail.com>
|
2026-08-25 16:32:28 -07:00 |
|
|
Canlin Guo
|
4f6885fffc
|
[DSV4][Kernel] Fuse shared experts into MegaMoE (#53040)
Signed-off-by: Canlin Guo <canlinguosdu@gmail.com>
|
2026-08-20 12:07:02 -07:00 |
|
|
Canlin GuoandNick Hill
|
455edc022b
|
[ModelRunnerV2] Support prompt embeds (#42963)
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Signed-off-by: Canlin Guo <961750412@qq.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
|
2026-08-17 21:58:50 +00:00 |
|
|
Canlin Guo
|
5370461649
|
[BugFix][KV Cache] Fix hybrid prefix caching with hidden-state extraction (#51108)
Signed-off-by: Canlin Guo <canlinguosdu@gmail.com>
|
2026-08-06 06:42:37 +00:00 |
|
|
Canlin Guo
|
edbc4969a7
|
[Kernel][Inkling] Fuse shared-expert partial addition into the Lamport collective (#50697)
Signed-off-by: Canlin Guo <canlinguosdu@gmail.com>
|
2026-08-04 18:41:35 +00:00 |
|
|
Canlin Guo
|
33ef67e9fb
|
[BugFix] Increase the max supported duration for MOSS-TD (#49403)
Signed-off-by: Canlin Guo <canlinguosdu@gmail.com>
|
2026-07-25 14:48:12 +00:00 |
|
|
Canlin Guo
|
36484e464a
|
[BugFix] Restore full tokens for Qwen MTP When MoE SP (#48429)
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
|
2026-07-13 13:29:41 +08:00 |
|
|
Canlin Guoandyewentao256
|
a02984ed47
|
[Perf][Qwen] Replace MOE all-reduce with reduce-scatter (#47006)
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>
|
2026-07-12 06:14:49 +00:00 |
|
|
Canlin Guo
|
285c08c036
|
[Model] Support MOSS-Transcribe-Diarize (#47729)
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
|
2026-07-08 04:05:45 -07:00 |
|
|
Canlin Guo
|
2228fe6868
|
[Attention] Move FA3→FA4 upgrade into get_flash_attn_version() (#40815)
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
|
2026-05-05 15:43:03 +00:00 |
|
|
Canlin Guo
|
fe36bf5e80
|
[Model] Remove the unnecessary dtype conversion in MiniCPM (#32523)
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
|
2026-01-18 08:07:28 +00:00 |
|
|
Canlin Guo
|
7d6da483b0
|
[Minor][Clean] Remove the legacy assertion in video (#29150)
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
|
2025-11-20 23:52:34 -08:00 |
|
|
Canlin Guoand凌葭
|
fe25772aa9
|
[Bugfix] Handle broken frames in video loading (#29001)
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Signed-off-by: 凌葭 <lvjiang.lj@alibaba-inc.com>
Co-authored-by: 凌葭 <lvjiang.lj@alibaba-inc.com>
|
2025-11-20 04:38:12 +00:00 |
|
|
Canlin Guo
|
b9489f51e1
|
[Model][Perf] Use cos and sin cache in QwenVL (#28798)
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
|
2025-11-18 11:51:54 +00:00 |
|
|
Canlin Guo
|
bc5bd45c7d
|
[Refactor] Remove redundant TP gather/split in split_qkv in QwenVL (#28271)
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
|
2025-11-12 15:56:47 +00:00 |
|