phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-18 10:08:40 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Docs for meta-reference-gpu

Browse source
This commit is contained in:
Ashwin Bharambe 2024-11-18 13:58:12 -08:00
parent 38563d7c00
commit dd732f037f
9 changed files with 374 additions and 101 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama_stack/providers/inline/inference/meta_reference/generation.py
View file

@ -107,7 +107,7 @@ class Llama:
sys.stdout = open(os.devnull, "w")
start_time = time.time()
if config.checkpoint_dir:
if config.checkpoint_dir and config.checkpoint_dir != "null":
ckpt_dir = config.checkpoint_dir
else:
ckpt_dir = model_checkpoint_dir(model)
@ -137,7 +137,6 @@ class Llama:
), f"model_args vocab = {model_args.vocab_size} but tokenizer vocab = {tokenizer.n_words}"
if isinstance(config, MetaReferenceQuantizedInferenceConfig):
if isinstance(config.quantization, Fp8QuantizationConfig):
from .quantization.loader import convert_to_fp8_quantized_model