hanzoai/musetalk-bench
2
0
Fork 0
mirror of https://github.com/hanzoai/musetalk-bench.git synced 2026-10-30 18:27:32 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
main
musetalk-bench/patches
T
History
zeekayandHanzo Dev 501e62a4f8 perf(metal): cache compiled MPSGraph conv per shape -> fixes UNet regression 
Per-conv MPSGraph::new()+compile was a net loss on the UNets many small convs
(64->88ms). Caching the compiled graph+placeholders per (shape,dtype,params):
UNet back to 62ms (baseline parity), FULL-FAST 5.38->10.42 fps, full-VAE
1.04->2.24 fps. cosine still 1.000000.

Co-authored-by: Hanzo Dev <[email protected]>
2026-06-16 11:29:14 -07:00
..
metal-mpsconv
perf(metal): cache compiled MPSGraph conv per shape -> fixes UNet regression
2026-06-16 11:29:14 -07:00
conv.cu.diff
baseline: spark authoritative musetalk-bench (cuda src) before metal gating
2026-06-15 19:48:32 -07:00
cudnn.rs.diff
baseline: spark authoritative musetalk-bench (cuda src) before metal gating
2026-06-15 19:48:32 -07:00
hanzo-ml-conv-spatial-routing.patch
baseline: spark authoritative musetalk-bench (cuda src) before metal gating
2026-06-15 19:48:32 -07:00
hanzo-ml-cudnn-winograd-fallback.rs.snippet
baseline: spark authoritative musetalk-bench (cuda src) before metal gating
2026-06-15 19:48:32 -07:00
mod.rs.diff
baseline: spark authoritative musetalk-bench (cuda src) before metal gating
2026-06-15 19:48:32 -07:00
taesd_conv.cuh.new
baseline: spark authoritative musetalk-bench (cuda src) before metal gating
2026-06-15 19:48:32 -07:00