llama.cpp: Add speculative decoding (#6891)

This commit is contained in:
oobabooga 2025-04-23 20:10:16 -03:00 committed by GitHub
parent 9424ba17c8
commit e99c20bcb0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 61 additions and 2 deletions

View file

@ -145,6 +145,11 @@ def list_model_elements():
'cpp_runner',
'trust_remote_code',
'no_use_fast',
'model_draft',
'draft_max',
'gpu_layers_draft',
'device_draft',
'ctx_size_draft',
]
return elements