llama.cpp
Avoid fp32->fp16->fp32 conversion on cdna in ggml_cuda_op_mul_mat_cublas
#11356
Merged

Avoid fp32->fp16->fp32 conversion on cdna in ggml_cuda_op_mul_mat_cublas #11356

IMbackK
IMbackK IMbackK requested a review from JohannesGaessler JohannesGaessler 354 days ago
github-actions github-actions added Nvidia GPU
github-actions github-actions added ggml
IMbackK
JohannesGaessler
JohannesGaessler approved these changes on 2025-01-24
IMbackK
JohannesGaessler
IMbackK IMbackK force pushed 352 days ago
IMbackK
IMbackK Avoid fp32->fp16->fp32 conversion on cdna in ggml_cuda_op_mul_mat_cublas
9d9ac6aa
IMbackK IMbackK force pushed to 9d9ac6aa 352 days ago
JohannesGaessler
JohannesGaessler JohannesGaessler merged 9fbadaef into master 352 days ago
JohannesGaessler

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone