llama.cpp
434b2a1f
- ggml-webgpu: add Q1_0 support (#22374)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
17 days ago
ggml-webgpu: add Q1_0 support (#22374) * add fast matmul matvec q1_0 kernel * ggml-webgpu: drop redundant zero-fills in Q1_0 shmem init
References
#22374 - ggml-webgpu: add Q1_0 support
Author
SharmaRithik
Parents
983ca899
Loading