phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Distribution server now functioning

Browse source
This commit is contained in:
Ashwin Bharambe 2024-08-02 13:37:40 -07:00
parent 041cafbee3
commit 2cf9915806
21 changed files with 635 additions and 266 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_toolchain/inference/generation.py
View file

@ -29,7 +29,7 @@ from llama_models.llama3_1.api.model import Transformer
from llama_models.llama3_1.api.tokenizer import Tokenizer
from termcolor import cprint
from .api.config import CheckpointType, InlineImplConfig
from .api.config import CheckpointType, MetaReferenceImplConfig
from .api.datatypes import QuantizationType
@ -42,7 +42,7 @@ class TokenResult:
class Llama:
@staticmethod
def build(config: InlineImplConfig):
def build(config: MetaReferenceImplConfig):
"""
Build a Llama instance by initializing and loading a model checkpoint.