Skip to content

Pull requests: hw-native-sys/simpler

New pull request New
27 Open 1,637 Closed
27 Open 1,637 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

Refactor: hbg records and ships Definitions in one retained block
#1988 opened Aug 24, 2026 by ChaoWao Collaborator Loading…
5 tasks done
1
Fix: stabilize depth-two chip run lifecycle
#1987 opened Aug 24, 2026 by high-cloud Contributor • Draft
1
Extend a2a3 halMemCtl EACCES retry window
#1986 opened Aug 24, 2026 by luohuan19 Contributor Loading…
5
Refactor: hbg sizes its graph heap from what orchestration used
#1985 opened Aug 24, 2026 by poursoul Collaborator Loading…
4 of 5 tasks
8
Fix: support explicit L3 task dependencies
#1984 opened Aug 24, 2026 by YunjiQin Contributor Loading…
4 tasks done
1
3
CI: give scope-stats the DFX smoke step the other four have
#1983 opened Aug 24, 2026 by ChaoWao Collaborator Loading…
3 tasks done
1
Fix: size HBG ready queues from reachable tasks
#1982 opened Aug 24, 2026 by TaoZQY Contributor Loading…
1
1
Refactor: finish the PTO2 retirement, one identifier per commit
#1980 opened Aug 24, 2026 by ChaoWao Collaborator Loading…
8 tasks done
1
Support: record torch backend autoload state
#1977 opened Aug 24, 2026 by Crane-Liu Contributor Loading…
1
2
Refactor: split the L2 tensor argument from each runtime's working tensor
#1974 opened Aug 24, 2026 by ChaoWao Collaborator Loading…
5 of 6 tasks
1
Fix: prefer staging views for host tensor access
#1973 opened Aug 24, 2026 by TaoZQY Contributor Loading…
7 tasks done
1
7
Add: allocate Qwen args in pinned host memory
#1971 opened Aug 24, 2026 by yanghaoran29 Contributor Loading…
4 tasks done
6
Fix: align full-rank chip run activation
#1967 opened Aug 23, 2026 by high-cloud Contributor • Draft
1
Name a device allocation by identity, and judge reach in one vocabulary
#1953 opened Aug 21, 2026 by YunjiQin Contributor Loading…
3 of 4 tasks
10
Fix: redirect host spans to per-process buffered files
#1945 opened Aug 21, 2026 by high-cloud Contributor Loading…
10
test(st): L3 dispatch runs the callable it names
#1938 opened Aug 20, 2026 by vloncar Loading…
5
Fix: validate HBG single-ring boundaries
#1917 opened Aug 20, 2026 by zmnobug Contributor Loading…
3 tasks done
17
Support: add l2-orchestrator-standalone bench for the L2 submit path
#1903 opened Aug 19, 2026 by network4agent Loading…
1
Perf: copy all Graph submission PODs to the device in one bulk H2D
#1890 opened Aug 19, 2026 by yanghaoran29 Contributor Loading…
5 of 6 tasks
4
Add MPI direct L3 transport, runtime, and vector-add example.
#1888 opened Aug 19, 2026 by xl1123 Contributor Loading…
17
Perf: pin Graph PODs and H2D each layer synchronously
#1872 opened Aug 18, 2026 by yanghaoran29 Contributor Loading…
2 tasks
12
Add: test host input refresh across L3 dispatches
#1856 opened Aug 17, 2026 by vegetabledoww Contributor Loading…
1
Perf: reuse retained L2 argument staging across HBG and TRB
#1854 opened Aug 17, 2026 by yanghaoran29 Contributor Loading…
5 of 6 tasks
14
Fix: support scope stats in host-built graphs
#1840 opened Aug 14, 2026 by vegetabledoww Contributor • Draft
1
5
tensormap_and_ringbuffer: 1-hop transitive reduction of redundant WAIT edges
#1830 opened Aug 13, 2026 by ChaoZheng109 Collaborator Loading…
1
16
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.