whisper.cpp
f32e6fa0 - ggml : remove GGML_CUDA_PEER_MAX_BATCH_SIZE (llama/28177)

Commit

17 days ago

ggml : remove GGML_CUDA_PEER_MAX_BATCH_SIZE (llama/28177) Signed-off-by: Adrien Gallouët <angt@huggingface.co>

References

Author

angt

Committer

ggerganov

Parents