-
Notifications
You must be signed in to change notification settings - Fork 660
Pull requests: PaddlePaddle/FastDeploy
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[Cherry-Pick][Optimization] supports mtp split_kv_attn(#5343)
#5344
opened Dec 2, 2025 by
carryyu
Loading…
5 tasks
[CI] Allow occasional distributed worker exit_code
#5341
opened Dec 2, 2025 by
EmmonsCurse
Loading…
5 tasks done
[PD Disaggregation] Simplify configuration for prefill-decode disaggregated deployment
#5340
opened Dec 2, 2025 by
liyonghua0910
•
Draft
5 tasks
[BugFix] Fix EP issue in the CUTLASS MoE backend
#5337
opened Dec 2, 2025 by
Sunny-bot1
Loading…
2 of 5 tasks
[BugFix] Fix issues related to data retrieval logic, parameter validation, and result serialization in both online and offline interfaces.
#5335
opened Dec 2, 2025 by
qwes5s5
Loading…
4 of 5 tasks
[Optimization] Remove version constraints for setuptools, uvicorn, triton and fastsafetensors
#5330
opened Dec 2, 2025 by
Echo-Nie
Loading…
2 of 5 tasks
[Feature] Support stopping the inference for the corresponding request in the online service after a disconnection request.
#5320
opened Dec 1, 2025 by
qwes5s5
Loading…
4 of 5 tasks
[PD Disaggregation] Add timestamp for analyzing splitwise deployment
#5317
opened Dec 1, 2025 by
juncaipeng
Loading…
5 tasks done
[Optimization]1.fix tp+ep moe_forward; 2.set max_prefill_batch=env.MAX_PREFILL_NUM
#5315
opened Dec 1, 2025 by
carryyu
Loading…
5 tasks
[Optimization] support mm prefill batch
#5313
opened Dec 1, 2025 by
kevincheng2
Loading…
3 of 5 tasks
Previous Next
ProTip!
Type g i on any issue or pull request to go back to the issue listing page.