apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-07 17:41:52 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

【Inference Optimize】DeepSeek-V3-model MLA Optimize (#3886)

Browse Source 
* support MLA chunk_size auto search & cuda_graph
This commit is contained in:
AIbin
2025-09-11 10:46:09 +08:00
committed by GitHub
parent 637d96c6ae
commit a7392a0ff9
23 changed files with 375 additions and 310 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastdeploy/model_executor/layers/attention/append_attn_backend.py
View File

@@ -141,6 +141,8 @@ class AppendAttentionBackend(AttentionBackend):
forward_meta.decoder_batch_ids,
forward_meta.decoder_tile_ids_per_batch,
forward_meta.decoder_num_blocks_cpu,
forward_meta.decoder_num_blocks_device,
forward_meta.decoder_chunk_size_device,
forward_meta.max_len_tensor_cpu,
forward_meta.encoder_batch_ids,
forward_meta.encoder_tile_ids_per_batch,