server: bench: enable flash_attn param
This commit is contained in:
parent
405385726e
commit
5668c79ea0
1 changed files with 1 additions and 0 deletions
|
@ -268,6 +268,7 @@ def start_server_background(args):
|
|||
server_args.extend(['--defrag-thold', "0.1"])
|
||||
server_args.append('--cont-batching')
|
||||
server_args.append('--metrics')
|
||||
server_args.append('--flash-attn')
|
||||
server_args.extend(['--log-format', "text"])
|
||||
args = [str(arg) for arg in [server_path, *server_args]]
|
||||
print(f"bench: starting server with: {' '.join(args)}")
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue