Skip to content

Pull requests: deepseek-ai/DeepEP

New pull request New
10 Open 52 Closed
10 Open 52 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Remove memory fence in NVLink barrier.
#253 opened Jun 24, 2025 by sphish Loading…
Tiny make test arguments configurable
#251 opened Jun 24, 2025 by fzyzcjy Loading…
Computation communication overlap
#249 opened Jun 24, 2025 by fzyzcjy • Draft
Optimize low latency combine recv kernel (about 2.7x speedup)
#248 opened Jun 23, 2025 by fzyzcjy Loading…
Support displaying separate send and recv time
#239 opened Jun 21, 2025 by fzyzcjy Loading…
Tiny support tests on systems with other number of GPUs
#238 opened Jun 20, 2025 by fzyzcjy Loading…
2
Optimize get_dispatch_layout from 170us to 45us
#232 opened Jun 20, 2025 by fzyzcjy Loading…
Refactor and support TMA for internode kernels
#225 opened Jun 19, 2025 by LyricZhao • Draft
Support other NVLink scenarios
#218 opened Jun 17, 2025 by fzyzcjy Loading…
1
Support cuMem API in cross process shared memory management
#217 opened Jun 17, 2025 by fzyzcjy Loading…
4
ProTip! Mix and match filters to narrow down what you’re looking for.