phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

Fix conversion to RawMessage everywhere

Browse source
This commit is contained in:
Ashwin Bharambe 2024-12-17 13:38:01 -08:00
parent fbca51d6da
commit b7a7caa9a8
11 changed files with 87 additions and 78 deletions
Download patch file Download diff file Expand all files Collapse all files

13
llama_stack/providers/inline/inference/meta_reference/generation.py
View file

@ -25,7 +25,6 @@ from fairscale.nn.model_parallel.initialize import (
)
from llama_models.llama3.api.args import ModelArgs
from llama_models.llama3.api.chat_format import ChatFormat, LLMInput
from llama_models.llama3.api.datatypes import RawContent, RawMessage
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 (
@ -39,6 +38,10 @@ from llama_stack.apis.inference import * # noqa: F403
from lmformatenforcer import JsonSchemaParser, TokenEnforcer, TokenEnforcerTokenizerData
from llama_stack.distribution.utils.model_utils import model_local_dir
from llama_stack.providers.utils.inference.prompt_adapter import (
ChatCompletionRequestWithRawContent,
CompletionRequestWithRawContent,
)
from .config import (
Fp8QuantizationConfig,
@ -50,14 +53,6 @@ from .config import (
log = logging.getLogger(__name__)
class ChatCompletionRequestWithRawContent(ChatCompletionRequest):
messages: List[RawMessage]
class CompletionRequestWithRawContent(CompletionRequest):
content: RawContent
def model_checkpoint_dir(model) -> str:
checkpoint_dir = Path(model_local_dir(model.descriptor()))