ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update llama.py

Browse source
This commit is contained in:
Daniel Han 2025-03-14 04:02:41 -07:00
commit cb06d8576c
1 changed files with 4 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

8
unsloth/models/llama.py
View file

@ -2659,11 +2659,11 @@ class FastLlamaModel:
pass
# Patch for fast inference
vllm_engine = getattr(model, "vllm_engine", None)
vllm_engine = getattr(model.model, "vllm_engine", None)
if vllm_engine is not None:
model.vllm_engine = vllm_engine
model.fast_generate = vllm_fast_generate
model.fast_generate_batches = vllm_fast_generate_batches
model.vllm_engine = model.model.vllm_engine
model.fast_generate = model.model.vllm_fast_generate
model.fast_generate_batches = model.model.vllm_fast_generate_batches
# Also saving and loading LoRA
from unsloth_zoo.vllm_utils import save_lora, load_lora