phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-28 02:53:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

chore: remove dependency on llama_models completely (#1344)

Browse source
This commit is contained in:
Ashwin Bharambe 2025-03-01 12:48:08 -08:00 • committed by GitHub
parent 7131d5ddeb
commit 8bbd52bb9f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
43 changed files with 131358 additions and 202 deletions
Download patch file Download diff file Expand all files Collapse all files

14
llama_stack/providers/inline/inference/meta_reference/generation.py
View file

@ -23,13 +23,6 @@ from fairscale.nn.model_parallel.initialize import (
initialize_model_parallel,
model_parallel_is_initialized,
)
from llama_models.llama3.api.args import ModelArgs
from llama_models.llama3.api.chat_format import ChatFormat, LLMInput
from llama_models.llama3.api.tokenizer import Tokenizer
from llama_models.llama3.reference_impl.model import Transformer
from llama_models.llama3.reference_impl.multimodal.model import (
CrossAttentionTransformer,
)
from lmformatenforcer import JsonSchemaParser, TokenEnforcer, TokenEnforcerTokenizerData
from pydantic import BaseModel
@ -46,6 +39,13 @@ from llama_stack.models.llama.datatypes import (
SamplingParams,
TopPSamplingStrategy,
)
from llama_stack.models.llama.llama3.args import ModelArgs
from llama_stack.models.llama.llama3.chat_format import ChatFormat, LLMInput
from llama_stack.models.llama.llama3.model import Transformer
from llama_stack.models.llama.llama3.multimodal.model import (
CrossAttentionTransformer,
)
from llama_stack.models.llama.llama3.tokenizer import Tokenizer
from llama_stack.models.llama.sku_list import resolve_model
from llama_stack.providers.utils.inference.prompt_adapter import (
ChatCompletionRequestWithRawContent,