Fp8 paged attention update (#22222)
Signed-off-by: Xiao Yu <xiao.yu@amd.com> Signed-off-by: xiao-llm <xiao.yu.dc@outlook.com> Co-authored-by: Xiao Yu <xiao.yu@metamaterial.com> Co-authored-by: Xiao Yu <xiao.yu@amd.com> Co-authored-by: Bowen Bao <bowenbao@amd.com>
This commit is contained in:
co-authored by
Xiao Yu
Xiao Yu
Bowen Bao
parent
0e219cd50b
commit
01413e0cf5
+2
-1
@@ -19,4 +19,5 @@ void paged_attention(
|
||||
const std::optional<torch::Tensor>& query_start_loc, int64_t block_size,
|
||||
int64_t max_seq_len, const std::optional<torch::Tensor>& alibi_slopes,
|
||||
const std::string& kv_cache_dtype, torch::Tensor& k_scale,
|
||||
torch::Tensor& v_scale, const std::optional<torch::Tensor>& fp8_out_scale);
|
||||
torch::Tensor& v_scale, const std::optional<torch::Tensor>& fp8_out_scale,
|
||||
const std::string& mfma_type);
|
||||
|
||||
Reference in New Issue
Block a user