cabaf4eff3
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com> Signed-off-by: simon-mo <xmo@berkeley.edu> Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu> Co-authored-by: simon-mo <simon.mo@hey.com> Co-authored-by: Michael Goin <mgoin64@gmail.com> Co-authored-by: Zhuohan Li <zhuohan123@gmail.com> Co-authored-by: Tyler Michael Smith <tysmith@redhat.com> Co-authored-by: Alexander Matveev <59768536+alexm-neuralmagic@users.noreply.github.com> Co-authored-by: simon-mo <xmo@berkeley.edu>
39 lines
1.7 KiB
C++
39 lines
1.7 KiB
C++
#pragma once
|
|
|
|
#include <torch/all.h>
|
|
|
|
#include <map>
|
|
#include <vector>
|
|
|
|
void swap_blocks(torch::Tensor& src, torch::Tensor& dst,
|
|
const torch::Tensor& block_mapping);
|
|
|
|
// Note: the key_caches and value_caches vectors are constant but
|
|
// not the Tensors they contain. The vectors need to be const refs
|
|
// in order to satisfy pytorch's C++ operator registration code.
|
|
void copy_blocks(std::vector<torch::Tensor> const& key_caches,
|
|
std::vector<torch::Tensor> const& value_caches,
|
|
const torch::Tensor& block_mapping);
|
|
|
|
void reshape_and_cache(torch::Tensor& key, torch::Tensor& value,
|
|
torch::Tensor& key_cache, torch::Tensor& value_cache,
|
|
torch::Tensor& slot_mapping,
|
|
const std::string& kv_cache_dtype,
|
|
torch::Tensor& k_scale, torch::Tensor& v_scale);
|
|
|
|
void reshape_and_cache_flash(torch::Tensor& key, torch::Tensor& value,
|
|
torch::Tensor& key_cache,
|
|
torch::Tensor& value_cache,
|
|
torch::Tensor& slot_mapping,
|
|
const std::string& kv_cache_dtype,
|
|
torch::Tensor& k_scale, torch::Tensor& v_scale);
|
|
|
|
void concat_and_cache_mla(torch::Tensor& kv_c, torch::Tensor& k_pe,
|
|
torch::Tensor& kv_cache, torch::Tensor& slot_mapping,
|
|
const std::string& kv_cache_dtype,
|
|
torch::Tensor& scale);
|
|
|
|
// Just for unittest
|
|
void convert_fp8(torch::Tensor& dst_cache, torch::Tensor& src_cache,
|
|
const double scale, const std::string& kv_cache_dtype);
|