Skip to content

Pull requests: ROCm/mori

New pull request New
43 Open 508 Closed
43 Open 508 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

perf(ep): skip the nodeRecvTokenNum atomic when every chunk slot is signalled
#624 opened Aug 31, 2026 by isytwu Collaborator • Draft
SDMA HIP device management fixes
#623 opened Aug 31, 2026 by pemeliya Contributor • Draft
1 task
ci: cleanup stale mori containers before internode tests
#622 opened Aug 31, 2026 by QizhouZhang97 Contributor Loading…
1 task
fix(ep): correct recv-slice indexing in DispatchInterNodeRecv (v1 kernel)
#621 opened Aug 31, 2026 by isytwu Collaborator • Draft
3 tasks done
@isytwu
Refactor/umbp drop standalone client
#620 opened Aug 31, 2026 by TianDi101 Collaborator Loading…
1 task
perf(umbp): cut per-range overhead in local BatchGetRanges
#619 opened Aug 31, 2026 by isytwu Collaborator • Draft
@isytwu
allocator: add CCO-backed LSA symmetric windows
#618 opened Aug 28, 2026 by yangyuhuiling Contributor • Draft
5 tasks done
[Pre-flight] Add cluster-network-topology skill and scripts
#615 opened Aug 28, 2026 by lcskrishna • Draft
1 task
perf(ep): InterNodeV1LL low-token latency on MI300X + CX7
#614 opened Aug 28, 2026 by jhchouuu Collaborator • Draft
perf(ep): optimize InterNodeV1LL small-token latency on EP16
#613 opened Aug 28, 2026 by isytwu Collaborator • Draft
1 task
1
fix: use strided offsets in run_single_once when batch_contiguous is disabled
#612 opened Aug 27, 2026 by kudomcho Contributor Loading…
2 tasks done
perf(EPv2): size the gfx1250 combine pull tile against the LDS budget
#608 opened Aug 27, 2026 by zhangfei829 Collaborator Loading…
1
CCO SDMA micro optimizations
#603 opened Aug 25, 2026 by pemeliya Contributor Loading…
3
tune(ep/v2): give fp8 dispatch its own gfx1250 EP4 row
#598 opened Aug 24, 2026 by jhchouuu Collaborator Loading…
perf(ep): optimize IntraNode dispatch kernel for MI350X
#586 opened Aug 19, 2026 by kudomcho Contributor Loading…
6 tasks done
@kawhil-amd
4
Don't merge: AI NIC perf collection
#585 opened Aug 19, 2026 by amirakb89 Contributor • Draft
1 task
feat(umbp): GPU Direct Storage (hipfile) SSD-to-GPU read path
#579 opened Aug 19, 2026 by isytwu Collaborator Loading…
5 tasks done
@isytwu
feat(ep/v2): TDM dispatch transport for the flydsl backend
#578 opened Aug 18, 2026 by XingerZhu Loading…
1 task
Io prepared transfers v3
#574 opened Aug 17, 2026 by amirakb89 Contributor Loading…
4 tasks
5
Io cpp bench default
#573 opened Aug 17, 2026 by amirakb89 Contributor Loading…
6
test bnxt ci
#570 opened Aug 17, 2026 by QizhouZhang97 Contributor Loading…
Feat/env check gpu memory
#566 opened Aug 14, 2026 by amirakb89 Contributor Loading…
7
EP support for rail isolated topology through Host based RDMA
#558 opened Aug 13, 2026 by itej89 Loading…
1 task
@jhchouuu
25
feat(umbp): support the UMBP tree connector on a distributed backend
#547 opened Aug 12, 2026 by maning00 Contributor Loading…
refactor(umbp): make distributed mode backend- and transport-agnostic
#540 opened Aug 11, 2026 by TianDi101 Collaborator Loading…
ProTip! Follow long discussions with comments:>50.