-
Notifications
You must be signed in to change notification settings - Fork 78
Pull requests: hw-native-sys/simpler
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Refactor: hbg unifies the task progress byte into a sequential state enum
#2130
opened Sep 4, 2026 by
ChaoZheng109
Collaborator
Loading…
4 tasks done
examples: add standalone Qwen3 TMR decode benchmark
#2129
opened Sep 4, 2026 by
Crane-Liu
Contributor
Loading…
Refactor: make [STRACE] the only host-side timeline format
#2128
opened Sep 4, 2026 by
ChaoWao
Collaborator
Loading…
4 of 5 tasks
feat(dfx): unify chip-swimlane scheduler schema
#2127
opened Sep 4, 2026 by
zhusy54
Collaborator
Loading…
4 tasks done
Refactor: make the DFX collectors resident across runs
#2126
opened Sep 4, 2026 by
ChaoWao
Collaborator
Loading…
6 tasks done
Refactor: reduce the clock anchor to one offset reading
#2125
opened Sep 4, 2026 by
doraemonmj
Contributor
Loading…
Add: Worker.detach_persistent_domain public retention API
#2120
opened Sep 3, 2026 by
georgebisbas
Contributor
Loading…
3 of 4 tasks
feat(worker): add extensible chip-child control dispatch
#2116
opened Sep 3, 2026 by
superxf
Loading…
Add: SIMPLER_TENSOR_DATA_TIMEOUT_MS to override the tensor-data wait
#2114
opened Sep 3, 2026 by
ChaoZheng109
Collaborator
•
Draft
4 tasks done
feat(dfx): profile A5 HBG AICore scheduler
#2104
opened Sep 3, 2026 by
zhusy54
Collaborator
Loading…
feat(l3): Max/Min/Prod reduce ops for allreduce/reduce_scatter kernels
#2102
opened Sep 2, 2026 by
georgebisbas
Contributor
Loading…
2 of 3 tasks
Add: A5 RTT die-preflight scheduler placement
#2097
opened Sep 2, 2026 by
yanghaoran29
Contributor
Loading…
6 of 8 tasks
Add: comm region template and SPSC message queue
#2096
opened Sep 2, 2026 by
ccyywwen
Contributor
Loading…
Perf: align A5 TMR hot function entries
#2076
opened Aug 31, 2026 by
yanghaoran29
Contributor
•
Draft
Reduce redundant host_build_graph fanin edges
#2067
opened Aug 29, 2026 by
ChaoZheng109
Collaborator
Loading…
6 of 7 tasks
Add: an AUTO-scope twin of the qwen3_14b_decode scene test
#2066
opened Aug 29, 2026 by
ChaoZheng109
Collaborator
Loading…
Add: record scalar_count in the ChipCallable header
#2064
opened Aug 29, 2026 by
sunkaixuan2018
Contributor
•
Draft
Adapt simpler to unified PTO-ISA async workspace interface
#2059
opened Aug 28, 2026 by
wxwnnzdyd
Contributor
Loading…
Add: queue consecutive runs on shared streams
#2028
opened Aug 26, 2026 by
Crane-Liu
Contributor
Loading…
Feature: enable SDMA and URMA in the default A5 runtime
#2026
opened Aug 26, 2026 by
doraemonmj
Contributor
Loading…
Reduce redundant TMR WAIT edges with bounded bitmap
#2009
opened Aug 25, 2026 by
ChaoZheng109
Collaborator
Loading…
6 tasks done
Add: sustained four-chip step jitter reproducer
#1997
opened Aug 25, 2026 by
high-cloud
Contributor
Loading…
Fix: stabilize depth-two chip run lifecycle
#1987
opened Aug 24, 2026 by
high-cloud
Contributor
•
Draft
Add: allocate Qwen args in pinned host memory
#1971
opened Aug 24, 2026 by
yanghaoran29
Contributor
Loading…
4 tasks done
Previous Next
ProTip!
Follow long discussions with comments:>50.