-
Notifications
You must be signed in to change notification settings - Fork 55
Pull requests: hw-native-sys/pypto-lib
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Add: DeepSeek V4 Flash real-weight loading and numeric validation
enhancement
New feature or request
#964
opened Aug 14, 2026 by
lwDavid
Collaborator
Loading…
Add: track DeepSeek V4 performance history
#959
opened Aug 14, 2026 by
wangqin1723-max
Collaborator
Loading…
CI: install with uv and default the toolchain to bundle
#952
opened Aug 13, 2026 by
luohuan19
Contributor
Loading…
Add: compose DeepSeek V4 CSA decode TP output
#940
opened Aug 11, 2026 by
wangqin1723-max
Collaborator
Loading…
feat(dspark): add DeepSeek V4 draft pipeline
#939
opened Aug 11, 2026 by
hashiqiqixian
Contributor
Loading…
Add: compose DeepSeek V4 HCA decode TP output
#938
opened Aug 11, 2026 by
wangqin1723-max
Collaborator
Loading…
feat(qwen3): replace decode paged attention with PyPTO
#933
opened Aug 11, 2026 by
Little-oil
Contributor
Loading…
Fix deterministic DeepSeek split-K reductions
#927
opened Aug 10, 2026 by
high-cloud
Collaborator
•
Draft
Add: experimental shared-expert weight TP on fixed SP
#913
opened Aug 7, 2026 by
wangqin1723-max
Collaborator
Loading…
Add: prototype MXFP8 shared-expert down projection
#911
opened Aug 6, 2026 by
yanghaoran29
Contributor
•
Draft
EXPERIMENT (do not merge): A/B the A5 daily sweep against ptoas op fusion
wontfix
This will not be worked on
feat(dsv4): make MTP prefill chunk-safe
#883
opened Aug 1, 2026 by
vegetabledoww
Contributor
Loading…
Perf: assemble SWA decode window in L1, drop the GM gather
#882
opened Jul 31, 2026 by
Hzfengsy
Member
Loading…
CI: bench decode_attention_csa on fixed even/odd cards
#881
opened Jul 31, 2026 by
luohuan19
Contributor
Loading…
Fix(deepseek-v4 pro): let MoE post_ffn use automatic dependency tracking
#879
opened Jul 31, 2026 by
yanghaoran29
Contributor
Loading…
2 of 3 tasks
Perf: defer DSv4-flash attention RMSNorm reduce past the QKV projection
#846
opened Jul 27, 2026 by
Hzfengsy
Member
Loading…
WIP: dsv4-pro Hybrid MXFP8–MXFP4 operator rewrite
#836
opened Jul 25, 2026 by
yanghaoran29
Contributor
•
Draft
2 of 4 tasks
fix(deepseek-v4-flash): fit decode buffers for PTOAS planning
#827
opened Jul 24, 2026 by
Little-oil
Contributor
Loading…
[Docs] PyPTO 性能优化案例：DeepSeek-V4 MoE 预处理算子融合与同步开销复盘
#825
opened Jul 24, 2026 by
Little-oil
Contributor
Loading…
45 tasks
CI: disable all jobs, add A5 runner bring-up smoke job
#821
opened Jul 23, 2026 by
luohuan19
Contributor
Loading…
Previous Next
ProTip!
What’s not been updated in a month: updated:<2026-07-15.