oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-05 14:45:28 +00:00
Code Issues Projects Releases Packages Wiki Activity

llama.cpp: Use -1 instead of 0 for auto gpu_layers

Browse source
This commit is contained in:
oobabooga 2026-03-04 19:21:45 -08:00
parent d45aa6606a
commit fbfcd59fe0
4 changed files with 8 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

5
modules/llama_cpp_server.py
View file

@ -347,7 +347,7 @@ class LlamaServer:
"--flash-attn", "on",
]
if shared.args.gpu_layers > 0:
if shared.args.gpu_layers >= 0:
cmd += ["--gpu-layers", str(shared.args.gpu_layers), "--fit", "off"]
else:
cmd += ["--fit", "on"]
@ -448,7 +448,8 @@ class LlamaServer:
print(' '.join(str(item) for item in cmd[1:]))
print()
logger.info(f"Using gpu_layers={shared.args.gpu_layers} | ctx_size={shared.args.ctx_size} | cache_type={cache_type}")
gpu_layers_str = "auto" if shared.args.gpu_layers < 0 else str(shared.args.gpu_layers)
logger.info(f"Using gpu_layers={gpu_layers_str} | ctx_size={shared.args.ctx_size} | cache_type={cache_type}")
# Start the server with pipes for output
self.process = subprocess.Popen(
cmd,