 Cheng Wan
|
98aa836bbf
|
Overlap the gating function with shared experts in DeepSeek (#7978)
|
2025-07-12 13:41:50 -07:00 |
|
|
Cheng Wan
|
475a249bb8
|
temporarily disable deepep-8-gpu and activate two small tests (#7961)
|
2025-07-11 14:22:05 -07:00 |
|
|
Cheng Wan
|
d487555f84
|
[CI] Add deepep tests to CI (#7872)
|
2025-07-09 01:49:47 -07:00 |
|
|
Cheng Wan
|
6c903611ca
|
Fix incorrect spec_num_draft_tokens in draft_extend (#7757)
|
2025-07-05 02:18:16 -07:00 |
|
|
Cheng Wan
|
8fc910db03
|
DP Attention with Auto DeepEP Dispatch (#7222)
|
2025-07-05 01:54:24 -07:00 |
|
|
Cheng Wan
|
cb432f1770
|
saving hidden_states.clone() (#7705)
|
2025-07-04 20:07:42 -07:00 |
|
|
Cheng Wan
|
1b8cf77b01
|
[Fix] incorrect assert in EPLB (#7575)
|
2025-06-26 14:59:20 -07:00 |
|
|
Cheng Wan
|
f8d48fd311
|
Fix dtype for idle input in spec decoding (#7456)
|
2025-06-23 11:23:25 -07:00 |
|
|
Cheng Wan
|
ac5010e0ba
|
Fix CUDA Graph Check under Deepep with DP FFN (#7451)
|
2025-06-22 20:35:58 -07:00 |
|
|
Cheng Wan
|
5041df2d01
|
Fix 7285 Merge Conflicts (#7403)
|
2025-06-20 16:02:50 -07:00 |
|
|
Cheng Wan
|
256801e973
|
Update usage_processor.py (#7402)
|
2025-06-20 15:55:38 -07:00 |
|
|
Cheng Wan
|
73b13e69b4
|
Optimize DP attn scheduling for speculative decoding (#7285)
|
2025-06-20 15:06:41 -07:00 |
|
|
Cheng Wan
|
8609e637a9
|
Fix All-Gather under world size one (#7219)
|
2025-06-20 14:57:34 -07:00 |
|
|
Cheng Wan
|
22bfed7509
|
[DeepSeekNextN] fix: residual of head norm can be None (#7398)
|
2025-06-20 14:45:16 -07:00 |
|
|
Cheng Wan
|
e879d8b7a8
|
[Feature] Comprehensive Hybrid Parallelism Support (#6389)
|
2025-06-20 14:43:11 -07:00 |
|
|
Cheng Wan
|
3c2274fbee
|
Implement gather before attn (#6378)
|
2025-06-15 21:08:56 -07:00 |
|
|
Cheng Wan
|
499f5e620c
|
Fix one missing arg in DeepEP (#6878)
|
2025-06-04 19:14:47 -07:00 |
|
|
Cheng Wan
|
81964328b7
|
Set num_fused_shared_experts as num_shared_experts when shared_experts fusion is not disabled (#6736)
|
2025-06-04 15:53:22 -07:00 |
|
|
Cheng Wan
|
8a5480528d
|
[Refactor] Rename n_share_experts_fusion as num_fused_shared_experts (#6735)
|
2025-06-03 17:48:24 -07:00 |
|
|
Cheng Wan
|
ced3c07afe
|
Support token-level quantization for EP MoE (#6782)
|
2025-05-30 17:26:30 -07:00 |
|
|
Cheng Wan
|
b581b22504
|
Fix one bug in the grouped-gemm triton kernel (#6772)
|
2025-05-30 01:42:08 -07:00 |
|
|
Cheng Wan
|
a3d7f4b673
|
fix communicator for non-dp lm head (#6662)
|
2025-05-27 02:31:12 -07:00 |
|
|
|
b2e95f62b4
|
Fix two issues related to --moe-dense-tp-size=1 (#5657)
Co-authored-by: liusy58 <liusy58@linux.alibaba.com>
Co-authored-by: 颉沆 <xiehang.lsy@alibaba-inc.com>
|
2025-05-12 23:51:39 -07:00 |
|
|
Cheng Wanandliusy58
|
25c83fff6a
|
Performing Vocabulary Parallelism for LM Head across Attention TP Groups (#5558)
Co-authored-by: liusy58 <liusy58@linux.alibaba.com>
|
2025-05-11 23:36:29 -07:00 |
|
|
Cheng Wan
|
9bddf1c82d
|
Deferring 8 GPU test (#6102)
|
2025-05-07 18:49:58 -07:00 |
|
|
Cheng WanandByron Hsu
|
711efe7814
|
Integrating PD disaggregation with DP attention and DeepEP (#5435)
Co-authored-by: Byron Hsu <byronhsu1230@gmail.com>
|
2025-04-23 01:46:01 -07:00 |
|
|
Cheng Wan
|
6aca583420
|
Fix several minor issues in PD disaggregation (#5444)
|
2025-04-15 23:04:41 -07:00 |
|
|
Cheng Wan
|
038bc5d521
|
Support --enable-llama4-multimodal (#5254)
|
2025-04-11 01:24:14 -07:00 |
|
|
Cheng Wan
|
76c48a0913
|
[DeepEP] fix: import buffer error (#5179)
|
2025-04-08 22:12:14 -07:00 |
|
|
Cheng Wan
|
4c54f44202
|
[deepep] fix: shared experts are not initialized when shared experts fusion is enabled (#5072)
|
2025-04-04 15:08:30 -07:00 |
|
|
Cheng Wan
|
0d658ac3df
|
Support recording experts workload in QWen2-MoE (#4775)
|
2025-03-26 00:29:57 -07:00 |
|
|
Cheng Wan
|
7b5fc71972
|
fix SUPPORT_CUTLASS_BLOCK_FP8 flag (#4640)
|
2025-03-20 21:45:07 -07:00 |
|
|
Cheng Wan
|
3196999f63
|
Reduce computation and communication in DP attention (#4521)
|
2025-03-18 13:41:36 -07:00 |
|
|
Cheng WanandAbatom
|
2f6bacee03
|
[moe] fix: correct the cache size in the last chunk (#3679)
Co-authored-by: Abatom <abzhonghua@gmail.com>
|
2025-03-12 22:22:13 -07:00 |
|
|
Cheng Wan
|
6b0aeb58fd
|
[moe] optim: reduce memory consumption in fused_moe (#3692)
|
2025-02-20 02:25:05 +08:00 |
|