llama.cpp
8ced5f41
- Move to no timeout for WaitAny in graph submission to avoid deadlocks in some cases on llvm-pipe backends (#20618)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
13 days ago
Move to no timeout for WaitAny in graph submission to avoid deadlocks in some cases on llvm-pipe backends (#20618)
References
#20618 - ggml webgpu: Move to no timeout for WaitAny in graph submission to avoid deadlocks
Author
reeselevine
Parents
78d550b5
Loading