Add gather_indexer_k_quant_cache kernel (#25931)
Signed-off-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com> Signed-off-by: Simon Mo <simon.mo@hey.com> Signed-off-by: Chen Zhang <zhangch99@outlook.com> Co-authored-by: Simon Mo <simon.mo@hey.com> Co-authored-by: Yongye Zhu <zyy1102000@gmail.com> Co-authored-by: Chen Zhang <zhangch99@outlook.com>
This commit is contained in:
co-authored by
Simon Mo
Yongye Zhu
Chen Zhang
parent
cd9890544b
commit
127c8b782a
@@ -64,3 +64,11 @@ void indexer_k_quant_and_cache(
|
||||
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]
|
||||
Reference in New Issue
Block a user