-
Notifications
You must be signed in to change notification settings - Fork 79
Pull requests: hw-native-sys/pypto
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
revert: InsertCommFence pass — buggy ptoas 0.50 dependency (#2076)
#2138
opened Jul 24, 2026 by
YunjiQin
Collaborator
Loading…
1 of 2 tasks
fix(codegen): wrap scalar cacheinvalid in make_tensor_view for ptoas 0.50
#2137
opened Jul 24, 2026 by
georgebisbas
Contributor
Loading…
chore(toolchain): Update PTOAS to v0.51 and adapt ptoas discovery
#2135
opened Jul 24, 2026 by
luohuan19
Contributor
Loading…
feat(ir): PTOAS-planner intra-core multi-buffer for pipelined tile carries
#2133
opened Jul 24, 2026 by
lyfne123
Collaborator
Loading…
fix(ir): Normalize tile/tensor scalar operand dtype
#2132
opened Jul 24, 2026 by
Hzfengsy
Member
Loading…
fix(ir): Gather the operand's split axis at the V->C boundary
#2129
opened Jul 24, 2026 by
Hzfengsy
Member
Loading…
feat(ptoas): enable DeepSeek V4 decode memory planning
#2128
opened Jul 24, 2026 by
Little-oil
Contributor
Loading…
chore(runtime): bump simpler to c032e07e
#2119
opened Jul 23, 2026 by
Little-oil
Contributor
Loading…
2 tasks
feat(ir/dsl): MXFP8/MXFP4 tile DSL ops
#2117
opened Jul 23, 2026 by
yanghaoran29
Contributor
•
Draft
2 of 4 tasks
feat(distributed): Add pld.tensor.all_to_all_v (variable-size all-to-all)
#2112
opened Jul 22, 2026 by
georgebisbas
Contributor
Loading…
feat(ir): support odd automatic vector splits
#2107
opened Jul 22, 2026 by
lyfne123
Collaborator
Loading…
fix(ir): forbid tile.move in-place reuse (root fix for #2100), revert #2100 workarounds
#2106
opened Jul 22, 2026 by
YunjiQin
Collaborator
Loading…
3 tasks done
feat(distributed): host-orchestrated ring allreduce with builtin.tensor.allreduce_ring
#2094
opened Jul 20, 2026 by
georgebisbas
Contributor
Loading…
3 of 5 tasks
feat(ir): add pl.prefetch.* frontend for async GM->L2 prefetch
#2089
opened Jul 20, 2026 by
lyfne123
Collaborator
Loading…
feat(codegen): lower Tile SSA to explicit PTO target IR
#2057
opened Jul 15, 2026 by
lyfne123
Collaborator
Loading…
WIP: Add experimental DSA memory-planner adapter
#2052
opened Jul 14, 2026 by
tonibohnlein
Contributor
•
Draft
WIP: changes to run DeepSeek V4 on A5
enhancement
New feature or request
#2044
opened Jul 14, 2026 by
yanghaoran29
Contributor
•
Draft
4 of 6 tasks
fix(runtime): adapt CallConfig dump args rename
#2020
opened Jul 13, 2026 by
Little-oil
Contributor
Loading…
fix(codegen): dispatch dual_aiv_dispatch AIV kernels on both vector lanes
#2012
opened Jul 12, 2026 by
luohuan19
Contributor
Loading…
4 tasks done
fix(ir): propagate valid_shape through tile.reshape (partial-valid vectors)
#1979
opened Jul 8, 2026 by
tonibohnlein
Contributor
Loading…
fix(runtime): coerce enable_dep_gen to bool in _make_call_config
bug
Something isn't working
#1962
opened Jul 7, 2026 by
lwDavid
Contributor
Loading…
feat(passes): deliver ptoas multi-buffer double-buffering (same-slot + PtoAS)
#1953
opened Jul 6, 2026 by
lyfne123
Collaborator
Loading…
fix(runtime,backend): bound device compile fan-out; configurable ptoas timeout
#1928
opened Jul 2, 2026 by
Little-oil
Contributor
Loading…
feat(ops): add class-A tile/tensor ops a2a3 ST; fix expands/sels codegen; configurable ptoas timeout
#1905
opened Jun 30, 2026 by
Little-oil
Contributor
Loading…
Previous Next
ProTip!
Type g p on any issue or pull request to go back to the pull request listing page.