apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 16:48:03 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

load hadamard_block_size from config (#3797)

Browse Source
This commit is contained in:
Yuan Xiaolan
2025-09-05 17:07:58 +08:00
committed by GitHub
parent 41aee08982
commit 2cf55168ca
10 changed files with 60 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
fastdeploy/engine/engine.py
View File

@@ -401,10 +401,6 @@ class LLMEngine:
"FLAGS_use_append_attn": 1,
"NCCL_ALGO": "Ring",
"FLAGS_max_partition_size": int(os.getenv("FLAGS_max_partition_size", 1024)),
"FLAGS_hardamard_moe_block_size": int(os.getenv("FLAGS_hardamard_moe_block_size", 128)),
"FLAGS_hardamard_use_diagonal_block_matrix": int(
os.getenv("FLAGS_hardamard_use_diagonal_block_matrix", 0)
),
}
# environment variables needed by Dy2St
variables.update(