path	# lines of code
api_inference/inference-api.ipynb	174
llama_guard_4.ipynb	501
assisted_decoding/assisted_decoding.py	23
assisted_decoding/assisted_decoding_70B_3B.ipynb	353
local_inference/gptq_generation.py	23
local_inference/4bit_bnb.ipynb	125
local_inference/8bit_bnb.ipynb	121
local_inference/awq.ipynb	561
local_inference/fp8-405B.ipynb	149
local_inference/awq_generation.py	29
gradio_demos/chatbot_demo.py	52
gradio_demos/chatbot_demo.ipynb	1316
llama_guard/prompt_guard.ipynb	371
llama_guard/llama-guard-4.ipynb	435
llama_guard/llama_guard_3_1B.ipynb	7349
fine_tune/sft_vlm.py	66
fine_tune/Llama-Vision FT.ipynb	323
fine_tune/peft_finetuning.py	40
llama_rag/llama_rag_pipeline.ipynb	7687
performance_optimization/torch_compile.py	24
performance_optimization/deepspeed_zero3.yaml	22
performance_optimization/quantized_cache.py	24
performance_optimization/torch_compile_with_torchao.ipynb	152
performance_optimization/prompt_reuse.py	23