From 4eb0a29add7ca7255c3cf79354bfb630c7a4a531 Mon Sep 17 00:00:00 2001 From: Daniel Han Date: Fri, 14 Mar 2025 04:08:17 -0700 Subject: [PATCH] Update llama.py --- unsloth/models/llama.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py index 0f2996d212..893a09dd14 100644 --- a/unsloth/models/llama.py +++ b/unsloth/models/llama.py @@ -2662,8 +2662,8 @@ class FastLlamaModel: vllm_engine = getattr(model.model, "vllm_engine", None) if vllm_engine is not None: 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 + model.fast_generate = model.model.fast_generate + model.fast_generate_batches = model.model.fast_generate_batches # Also saving and loading LoRA from unsloth_zoo.vllm_utils import save_lora, load_lora