cache.h

#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 copy_blocks_mla(std::vector<torch::Tensor> const& kv_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);

void gather_and_maybe_dequant_cache(
    torch::Tensor const& src_cache,    // [NUM_BLOCKS, BLOCK_SIZE, ENTRIES...]
    torch::Tensor const& dst,          // [TOT_TOKENS, ENTRIES...]
    torch::Tensor const& block_table,  // [BATCH, BLOCK_INDICES]
    torch::Tensor const& cu_seq_lens,  // [BATCH+1]
    int64_t batch_size, const std::string& kv_cache_dtype,
    torch::Tensor const& scale,
    std::optional<torch::Tensor> seq_starts = std::nullopt);

// TODO(hc): cp_gather_cache need support scaled kvcahe in the future.
void cp_gather_cache(
    torch::Tensor const& src_cache,    // [NUM_BLOCKS, BLOCK_SIZE, ENTRIES...]
    torch::Tensor const& dst,          // [TOT_TOKENS, ENTRIES...]
    torch::Tensor const& block_table,  // [BATCH, BLOCK_INDICES]
    torch::Tensor const& cu_seq_lens,  // [BATCH+1]
    int64_t batch_size, std::optional<torch::Tensor> seq_starts = std::nullopt);

// Indexer K quantization and cache function
void indexer_k_quant_and_cache(
    torch::Tensor& k,             // [num_tokens, head_dim]
    torch::Tensor& kv_cache,      // [num_blocks, block_size, cache_stride]
    torch::Tensor& slot_mapping,  // [num_tokens]
    int64_t quant_block_size,     // quantization block size
    const std::string& scale_fmt);

// Extract function to gather quantized K cache
void cp_gather_indexer_k_quant_cache(
    const torch::Tensor& kv_cache,  // [num_blocks, block_size, cache_stride]
    torch::Tensor& dst_k,           // [num_tokens, head_dim]
    torch::Tensor& dst_scale,  // [num_tokens, head_dim / quant_block_size * 4]
    const torch::Tensor& block_table,   // [batch_size, num_blocks]
    const torch::Tensor& cu_seq_lens);  // [batch_size + 1]