oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-06 07:03:37 +00:00
Code Issues Projects Releases Packages Wiki Activity

llama.cpp: Remove the --flash-attn flag (it's always on now)

Browse source
This commit is contained in:
oobabooga 2025-08-30 20:27:32 -07:00
parent 7b80e9a2ad
commit 13876a1ee8
5 changed files with 0 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

2
modules/llama_cpp_server.py
View file

@ -318,8 +318,6 @@ class LlamaServer:
"--no-webui",
]
if shared.args.flash_attn:
cmd.append("--flash-attn")
if shared.args.threads > 0:
cmd += ["--threads", str(shared.args.threads)]
if shared.args.threads_batch > 0: