llama.cpp
ecafc671
- vulkan: use floating-point zero for storage-only FP16 in DIAG/TRI (#32379)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
10 hours ago
vulkan: use floating-point zero for storage-only FP16 in DIAG/TRI (#32379) * vulkan: Change integer zero to floating-point zero for storage-only FP16 in DIAG/TRI. Assisted-by: OpenAI Codex * delete narrow test
References
#32379 - vulkan: use floating-point zero for storage-only FP16 in DIAG/TRI
Author
Ngoroth
Parents
d4f5c260
Loading