 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
|
98b38de3f2
|
Fix: Safe RoPE Cache Expansion to Prevent Position-ID Out-of-Bounds in EAGLE + Long-Sequence Workloads (#11871)
|
2025-11-25 01:19:06 +08:00 |
|
|
YAMY
|
53fffefd5d
|
Upgrade flashmla kernel for NSA tp support (#13718)
|
2025-11-23 01:36:49 -08:00 |
|
|
YAMY
|
fa92441027
|
[DeepseekV3.2] Deepseek fp8 support for MHA path (#12964)
|
2025-11-20 11:13:36 -08:00 |
|
|
YAMY
|
190002c613
|
[Docs][DeepseekV3.2] Update deepseekv3.2 docs for mha short seq prefill (#12868)
|
2025-11-08 00:11:02 -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 |
|
|
YAMY
|
c8492978a1
|
Fix Illegal Instruction/IMA errors when using DP attention -- num_tokens_for_logprob calculation (#12115)
|
2025-10-25 12:28:26 -07:00 |
|
|
YAMY
|
80407b0493
|
Fix: Dynamic RoPE Cache Expansion to Prevent Position-ID Out-of-Bounds in EAGLE + Long-Sequence Workloads (#10788)
|
2025-10-19 11:37:43 +08:00 |
|
|
YAMYandXinyuan Tong
|
5a9170d993
|
Optimize copy_kv_cache for spec decoding (#11126)
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
|
2025-10-08 10:43:30 +08:00 |
|
|
|
b045841bae
|
Feature/function calling update (#2700)
Co-authored-by: Mingyuan Ma <mamingyuan2001@berkeley.edu>
Co-authored-by: Chayenne <zhaochen20@outlook.com>
Co-authored-by: shuaills <shishuaiuoe@gmail.com>
|
2025-01-26 09:57:51 -08:00 |
|