[Kernel][Amd] Add fp8 kv cache support for rocm custom paged attention (#8577)
This commit is contained in:
@@ -26,7 +26,8 @@ TORCH_LIBRARY_EXPAND(TORCH_EXTENSION_NAME, rocm_ops) {
|
||||
" Tensor context_lens, int block_size,"
|
||||
" int max_context_len,"
|
||||
" Tensor? alibi_slopes,"
|
||||
" str kv_cache_dtype) -> ()");
|
||||
" str kv_cache_dtype,"
|
||||
" float k_scale, float v_scale) -> ()");
|
||||
rocm_ops.impl("paged_attention", torch::kCUDA, &paged_attention);
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user