 Yongfei Xu
|
17031120b8
|
[DeepSeek v3.2][Bugfix] get_index_k_scale_buffer support cp (#18280)
|
2026-03-17 09:54:54 -07:00 |
|
|
Baizhou Zhang
|
be63f982b7
|
[V32/GLM5] Control the threshold of applying dense attention with an environ (#20062)
|
2026-03-09 14:36:10 -07:00 |
|
|
Xinyuan Tong
|
9ebffef1ef
|
[FIX] NSA backend page_table overflow in speculative decoding target_verify (#19016)
|
2026-03-05 16:04:58 -08:00 |
|
|
Rain Jiang
|
472eef4071
|
fa4 cleanup (#19727)
|
2026-03-05 17:54:25 +08:00 |
|
|
|
80a6b32703
|
[Perf] Optimize NSA backend metadata under MTP (#19536)
Co-authored-by: Baidu-AIAK <Baidu_AIAK@163.com>
Co-authored-by: zengpai <zengpai@baidu.com>
|
2026-03-01 01:59:26 -08:00 |
|
|
wufann
|
7e46aafebb
|
[AMD] Enable cudagraph for aiter nsa backend and add aiter impl for nsa pr… (#18526)
|
2026-02-27 13:18:32 -08:00 |
|
|
fxmarty-amd
|
9496bbd7b1
|
[AMD] Use tilelang as default NSA attention backend dispatch on AMD Instinct (#18319)
|
2026-02-27 01:43:34 -08:00 |
|
|
Bingxu Chenandmichaelzhang-ai
|
462267982b
|
[AMD] Fix mi35x dsv32 mtp nightly (#18978)
Co-authored-by: michaelzhang-ai <michaelzhang-ai@users.noreply.github.com>
|
2026-02-18 16:23:17 -08:00 |
|
|
Rain Jiang
|
0ffd0a3995
|
Nsa trtllm mla sparse fp8 support with Deepseek v3.2 NVFP4 (#18389)
|
2026-02-16 09:29:54 +08:00 |
|
|
Johnsonms
|
34132d6da5
|
Kernel: optimize decoding metadata in NSA multi-spec backend with fused kernels (#17554)
|
2026-02-14 16:40:15 +08:00 |
|
|
|
e8a2c13380
|
Deepseekv32 compatibility with transformers v5 (#18297)
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xiaoyu Zhang <35585791+BBuf@users.noreply.github.com>
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
|
2026-02-10 14:50:40 +08:00 |
|
|
Yongfei Xu
|
677f3c49da
|
[DeepSeek V3.2] [Bugfix] slice indexer and padding fa3 when can not run cuda graph (#17076)
|
2026-02-03 01:32:20 +08:00 |
|
|
Mohammad Miadh Angkad
|
1674b9ef44
|
[DeepSeek-V3.2] Fix TRT-LLM NSA in target_verify/draft_extend (#17662)
|
2026-01-25 13:10:14 +08:00 |
|
|
akhilg-nvandDarkSharpness
|
2fb328109f
|
[DeepSeek V3.2] Enable trtllm NSA with bf16 kvcache (#16758)
Co-authored-by: DarkSharpness <76582120+DarkSharpness@users.noreply.github.com>
|
2026-01-23 20:26:21 +08:00 |
|
|
Yongfei Xu
|
d2105d4abd
|
[DeepSeek v3.2] Opt MTP decode cuda batch sizes and nsa implementation (#16961)
|
2026-01-19 11:54:11 +08:00 |
|
|
Hubert Luandwufann
|
afe285f7bd
|
[AMD] enable CUDA graph for NSA backend and fix NSA FP8 fused RMSNorm group quant (#16841)
Co-authored-by: wufann <715544327@qq.com>
|
2026-01-13 17:36:01 -08:00 |
|
|
Baizhou Zhang
|
7d757d6f17
|
Clean Some Environment Variables for DeepSeek V32 (#15938)
|
2026-01-07 14:00:16 +08:00 |
|
|
Yongfei Xu
|
0d244116d2
|
[DeepSeek v3.2] opt Context Parallelism: support fused moe, multi batch and fp8 kvcache (#13959)
|
2026-01-02 23:49:14 +08:00 |
|
|
YL D
|
6afc5d497b
|
[DSv32] Move deep_gemm.get_paged_mqa_logits_metadata to init time as metadata (#15040)
|
2025-12-19 13:23:33 -08:00 |
|
|
b8zhong
|
e88e75a9df
|
[Deepseek V3.2] Fix Deepseek MTP in V1 mode (#15429)
|
2025-12-18 17:56:07 -08:00 |
|
|
Johnsonms
|
e0026f7c92
|
[Performance] optimize NSA backend metadata computation for multi-step speculative decoding (#14781)
|
2025-12-18 13:48:27 -08:00 |
|
|
b8zhongandBrayden Zhong
|
d20699a33c
|
[Deepseek V3.2] Support Overlap Spec + NSA (#15307)
Co-authored-by: Brayden Zhong <b8zhong@users.noreply.github.com>
|
2025-12-17 13:35:39 -08:00 |
|
|
YAMY
|
c96903074c
|
[NSA] Fix NSA backend assertion error when running DeepSeek-V3.2 PP with radix-cache (#15086)
|
2025-12-14 17:13:18 -08:00 |
|
|
YAMY
|
1f2b84d28d
|
Fix NSA Bug in Centralize NSA Dispatch Logic (#14245)
|
2025-12-01 13:18:18 -08:00 |
|
|
YAMY
|
decb48965d
|
[DeepSeekV3.2] Enable pure TP & Partial DP Attention (#13646)
|
2025-11-30 15:59:23 -08:00 |
|
|
YAMYandhlu1
|
5eed5fc0b0
|
[DeepSeekV3.2] Centralize NSA dispatch logic in NativeSparseAttnBackend (#13544)
Co-authored-by: hlu1 <14827759+hlu1@users.noreply.github.com>
|
2025-11-25 11:32:30 -08:00 |
|
|
YAMY
|
fa92441027
|
[DeepseekV3.2] Deepseek fp8 support for MHA path (#12964)
|
2025-11-20 11:13:36 -08:00 |
|
|
hlu1
|
a8fcbf6fe3
|
[Deepseek V3.2] Use torch.compile to speed up torch.cat in nsa (#13022)
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com>
|
2025-11-17 12:20:49 -08:00 |
|
|
lixiaolx
|
d368c7451a
|
(1/n)support context parallel with deepseekv3.2-DSA (#12065)
|
2025-11-16 20:12:25 -08:00 |
|
|
hlu1
|
a7002e614b
|
[Deepseek V3.2] Clean up MTP (#13236)
|
2025-11-14 11:01:37 -08:00 |
|
|
bingpsandGuangda Liu
|
4eda9969e8
|
[DeepseekV32]: use _concat_mla_absorb_q_general to replace torch.cat (#12215)
Co-authored-by: Guangda Liu <bingps@users.noreply.github.com>
|
2025-11-12 15:20:01 -08:00 |
|
|
hlu1
|
0d4a418424
|
[Deepseek V3.2] Fix accuracy bug in the Indexer (#12583)
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com>
|
2025-11-11 16:15:26 -08:00 |
|
|
YAMY
|
7257525cce
|
[DeepSeek-V3.2][NSA] Enable MHA Pathway for Short Sequence Prefill on B200 (SM100) (#12788)
|
2025-11-06 17:26:08 -08:00 |
|
|
YAMY
|
f235498eca
|
DeepSeek-V3.2: Add Adaptive MHA Attention Pathway for Short-Sequence Prefill (#11892)
|
2025-11-05 19:33:26 -08:00 |
|
|
Baizhou Zhang
|
621dfb8886
|
Import flash_mla from sgl-kernel (#12135)
|
2025-10-29 23:54:21 -07:00 |
|
|
hlu1
|
42e1a72efb
|
[Deepseek V3.2] Enable flashmla_auto with MTP (#12294)
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com>
|
2025-10-28 23:51:20 -07:00 |
|
|
hlu1
|
81a632ace6
|
[DeepseekV32] Enable flashmla_prefill kernel with fp8 kvcache (#11655)
Signed-off-by: Hao Lu <14827759+hlu1@users.noreply.github.com>
|
2025-10-27 23:11:48 -07:00 |
|
|
Baizhou Zhang
|
ef4a8097b8
|
Rename flashmla kernel options of nsa backend for better readability (#11876)
|
2025-10-21 13:14:16 -07:00 |
|
|
PaiiiiandPaiiiiiiiiiiiiii
|
efa473348b
|
[Spec Decoding] Support MTP for dsv3.2 (#11652)
Co-authored-by: Paiiiiiiiiiiiiii <zengpai@baidu.com>
|
2025-10-19 23:44:22 +08:00 |
|
|
Chang Su
|
627974405d
|
[Lint] Add python/sglang to ruff F401 checks and remove unused imports in files (#11685)
|
2025-10-17 16:49:46 -07:00 |
|
|
+2
|
efbc687c28
|
Support DeepSeek V3.2 Exp (#11061)
Co-authored-by: Stefan He <11166516+hebiao064@users.noreply.github.com>
Co-authored-by: Liangsheng Yin <95566987+hnyls2002@users.noreply.github.com>
Co-authored-by: Baizhou Zhang <56809903+fridge003@users.noreply.github.com>
Co-authored-by: DarkSharpness <76582120+darksharpness@users.noreply.github.com>
Co-authored-by: ZhengdQin <46387172+zhengdqin@users.noreply.github.com>
Co-authored-by: DarkSharpness <2040703891@qq.com>
Co-authored-by: hnyls2002 <lsyincs@gmail.com>
Co-authored-by: Zhengda Qin <zhengdqin@gmail.com>
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
Co-authored-by: HAI <hixiao@gmail.com>
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
|
2025-10-06 00:24:15 -07:00 |
|