llama.cpp
24f5bf8a - ggml : remove GGML_CUDA_PEER_MAX_BATCH_SIZE (#28177)

Commit

4 days ago

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

References

Author

angt

Parents