-
Notifications
You must be signed in to change notification settings - Fork 32
Pull requests: hw-native-sys/pypto-lib
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
perf(deepseek-v4): tune prefill sparse attention
#394
opened May 27, 2026 by
sjduan
Contributor
Loading…
Speed up Qwen3-14B LM head matmul and add standalone test driver
#391
opened May 26, 2026 by
luohuan19
Contributor
Loading…
chore(dsv4): migrate chunked_loop_optimizer to auto_chunk (#388)
#389
opened May 26, 2026 by
wangqin1723-max
Contributor
Loading…
Add Cayley-Hamilton triangular inverse example
#357
opened May 22, 2026 by
ChristosMatzoros
•
Draft
2 of 4 tasks
Update spmd2 version of decode_layer.py
#335
opened May 20, 2026 by
xzhxzhxzh123
Collaborator
Loading…
Update: reduce DeepSeek V4 sparse attention tasks
#301
opened May 16, 2026 by
high-cloud
Contributor
•
Draft
Fuse final RMSNorm + LM-head into qwen3_decode_all
#295
opened May 15, 2026 by
wangqin1723-max
Contributor
Loading…
Perf: bump Qwen3-14B decode_full scope-3 K_CHUNK 128 -> 256
#275
opened May 14, 2026 by
wangqin1723-max
Contributor
Loading…
golden: integrate pre-runtime pass IR validation into runner
#162
opened Apr 23, 2026 by
wuzhf9
Contributor
Loading…
ProTip!
What’s not been updated in a month: updated:<2026-04-26.