Skip to content

Pull requests: jd-opensource/xllm

New pull request New
9 Open 146 Closed
9 Open 146 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

bugfix: clear outdated tensors to save memory.
#198 opened Sep 26, 2025 by JimHsiung Loading…
bugfix: remove redundant aclrtSynchronizeStream calls by synchronizing once at exit in gtest.
#196 opened Sep 26, 2025 by yingxudeng Loading…
feat: improve overall prediction accuracy through separating prefill and decode.
#190 opened Sep 26, 2025 by weizhehuang0827 Loading…
feat: add acl graph executor.
#182 opened Sep 25, 2025 by zhang-minchao Loading…
20
feat: support dit model batch inference.
#179 opened Sep 25, 2025 by yiming-l21 Loading…
feat: support multithreaded building raw_forward_input.
#156 opened Sep 22, 2025 by yjw258 Loading…
13
feat: support multi_stream_parallel and modify model. [4/4]
#155 opened Sep 22, 2025 by guojinrong-nn Loading…
30
feat: add initial version of Online-Offline Co-location (OOC) scheduler.
#131 opened Sep 14, 2025 by tzh21 Loading…
23
feat: support continuous kvcache using virtual memory.
#92 opened Sep 4, 2025 by XuZhang99 Loading…
15
ProTip! Add no:assignee to see everything that’s not assigned.