-
Notifications
You must be signed in to change notification settings - Fork 27
Pull requests: hw-native-sys/pypto-serving
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
ci: isolate PR230 SDMA initialization failures (do not merge)
#232
opened Sep 11, 2026 by
vegetabledoww
Contributor
•
Draft
Use PyPTO's persistent JIT cache in serving
#231
opened Sep 11, 2026 by
lyfne123
Contributor
Loading…
fix: use 32 distinct prompts for DSV4 aligned profiling
#230
opened Sep 10, 2026 by
vegetabledoww
Contributor
Loading…
docs: add model integration guide, env-vars reference, and model support matrix
#228
opened Sep 10, 2026 by
LyuJiayi654
Loading…
perf(serving): reduce async scheduling overhead
#221
opened Sep 7, 2026 by
high-cloud
Contributor
Loading…
perf(deepseek): build decode block tables without a temporary per row
#206
opened Aug 27, 2026 by
lterrac
Collaborator
Loading…
Revert "perf(deepseek): reduce fused MTP decode host transfers"
#186
opened Aug 24, 2026 by
ndleslx
Collaborator
Loading…
feat(deepseek): add optional MoE expert statistics dump
#185
opened Aug 23, 2026 by
high-cloud
Contributor
•
Draft
feat(deepseek): expand continuous batching across fixed kernels
#145
opened Aug 7, 2026 by
hashiqiqixian
•
Draft
feat(skills): add DeepSeek V4 online SA_PROFILE perf skill
#121
opened Jul 28, 2026 by
sunghajung6688
Contributor
Loading…
[feature] TQ serving: add TurboQuant prefill/decode branch alongside …
#114
opened Jul 24, 2026 by
sunghajung6688
Contributor
Loading…
ci: prevent orphaned DeepSeek V4 engines on test interruption
#86
opened Jul 14, 2026 by
luohuan19
Contributor
Loading…
decouple qwen3 serving from lib contract
#85
opened Jul 14, 2026 by
bumble0918
Collaborator
Loading…
Previous Next
ProTip!
Follow long discussions with comments:>50.