DeepSeek/FlashMLA
1
0
Fork 0
mirror of https://github.com/deepseek-ai/FlashMLA synced 2025-06-26 18:15:54 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

update fp8 api

Browse Source
This commit is contained in:
chenhongmin.will
2025-02-26 08:32:05 +08:00
parent ef644a56e0
commit 4b314cd655
2 changed files with 27 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
csrc/flash_mla.h
View File

@@ -17,6 +17,9 @@ struct Flash_fwd_mla_params {
void *__restrict__ o_ptr;
void *__restrict__ softmax_lse_ptr;
float* __restrict__ descale_q_ptr = nullptr;
float* __restrict__ descale_k_ptr = nullptr;
index_t q_batch_stride;
index_t k_batch_stride;
index_t v_batch_stride;