Add profile presets and min-p controls, embeddings and VoxCPM workers
This commit is contained in:
1 parent
74dd2ed8ba
commit
a7b30b62d2
32 files changed
+615
-64
No files matched your search
+1
-1
@@ -240,7 +240,7 @@ class LlamaWorker:
|
||||
if cancel():raise InferenceError('Modellstart abgebrochen.')
|
||||
if plan_only:return
|
||||
with self.lock:self.phase='Modell wird geladen'
|
||||
launch=common+extra+vision_args+['--gpu-layers',str(layers),'--fit','off','--kv-unified','--threads',str(params['threads']),'--load-mode','none','--host','127.0.0.1','--alias',profile['name'],'--metrics','--no-webui','--log-disable']
|
||||
launch=common+extra+vision_args+['--min-p',str(params.get('min_p',0.0)),'--gpu-layers',str(layers),'--fit','off','--kv-unified','--threads',str(params['threads']),'--load-mode','none','--host','127.0.0.1','--alias',profile['name'],'--metrics','--no-webui','--log-disable']
|
||||
if mtp:launch+=['--spec-type','draft-mtp','--spec-draft-n-max',str(params.get('mtp_tokens',2)),'--spec-draft-p-min',str(params.get('mtp_min_p',.05)),'--spec-draft-type-k','f16','--spec-draft-type-v','f16']
|
||||
self.root.mkdir(parents=True,exist_ok=True,mode=0o700)
|
||||
with socket.socket() as sock:sock.bind(('127.0.0.1',0));port=sock.getsockname()[1]
|
||||
|
||||
Reference in new issue
Block a user