-
Notifications
You must be signed in to change notification settings - Fork 3k
Pull requests: PaddlePaddle/PaddleNLP
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[DCU]add op reshape_and_cache for dcu paged_attention
#10233
opened Mar 20, 2025 by
yongqiangma
Loading…
2 tasks
[DCU]support dcu PagedAttention prefix in compute_mla_absorb
#10229
opened Mar 20, 2025 by
zhanghonggeng
Loading…
2 tasks
【Inference Optimize】Paddle supports MOE model EP parallel
#10201
opened Mar 19, 2025 by
chang-wenbin
Loading…
2 tasks
fix rng_state checkpoint error when tp8
#10187
opened Mar 19, 2025 by
blacksheep-Aristotle
Loading…
2 tasks
【Inference Fix BUG】fix mix model save_output
#10185
opened Mar 18, 2025 by
chang-wenbin
Loading…
2 tasks
[Infer] Change groupwise weight quant from cpu to gpu for deepseek_v2 model
contributor
#10174
opened Mar 18, 2025 by
zeroRains
Loading…
2 tasks done
Add custom op for Tokens zip and unzip, in preparation of using groupgemm
#10169
opened Mar 17, 2025 by
A-nnonymous
Loading…
Added regroup padded op to perform token regroup using 1D expert_idx with max-token-per-expert padding
#10164
opened Mar 17, 2025 by
A-nnonymous
Loading…
Previous Next
ProTip!
no:milestone will show everything without a milestone.