Skip to content

vllm renamed AnyTokenizer to TokenizerLike. #3005

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
access2rohit merged 2 commits into from
Mar 3, 2026
+6 −6
Merged

vllm renamed AnyTokenizer to TokenizerLike. #3005

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c382e9f
upgrade vllm to v0.16.0
access2rohit Mar 3, 2026
2b4874c
vllm renamed AnyToeknizer to TokenizerLike. Updating DJL code
access2rohit Mar 3, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions engines/python/setup/djl_python/lmi_vllm/request_response_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@
)
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
from vllm.logprobs import Logprob
from vllm.transformers_utils.tokenizer import AnyTokenizer
from vllm.tokenizers import TokenizerLike

from djl_python.outputs import Output
from djl_python.async_utils import create_non_stream_output, create_stream_chunk_output
Expand Down Expand Up @@ -101,7 +101,7 @@ def convert_lmi_schema_to_completion_request(

def convert_completion_logprobs_to_tgi_tokens(
completion_logprobs: CompletionLogProbs,
tokenizer: AnyTokenizer,
tokenizer: TokenizerLike,
) -> List[dict]:
token_logprobs = completion_logprobs.token_logprobs
tokens = completion_logprobs.tokens
Expand Down Expand Up @@ -138,7 +138,7 @@ def convert_completion_response_to_lmi_schema(
response: CompletionResponse,
request: CompletionRequest = None,
include_details: bool = False,
tokenizer: AnyTokenizer = None,
tokenizer: TokenizerLike = None,
) -> Output:
primary_choice = response.choices[0]
lmi_response = {"generated_text": primary_choice.text}
Expand Down Expand Up @@ -258,7 +258,7 @@ def convert_completion_chunk_response_to_lmi_schema(
def lmi_with_details_non_stream_output_formatter(
response: CompletionResponse,
request: CompletionRequest = None,
tokenizer: AnyTokenizer = None,
tokenizer: TokenizerLike = None,
) -> Output:
return convert_completion_response_to_lmi_schema(response,
include_details=True,
Expand All @@ -269,7 +269,7 @@ def lmi_with_details_non_stream_output_formatter(
def lmi_non_stream_output_formatter(
response: CompletionResponse,
request: CompletionRequest = None,
tokenizer: AnyTokenizer = None,
tokenizer: TokenizerLike = None,
) -> Output:
return convert_completion_response_to_lmi_schema(response,
include_details=False,
Expand Down
2 changes: 1 addition & 1 deletion serving/docker/lmi-container-requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,6 @@ sentence-transformers==3.3.1
optimum==1.23.2
llmcompressor==0.9.0.1
mpi4py==4.0.1
https://djl-ai.s3.us-east-1.amazonaws.com/publish/vllm/vllm-0.15.1-cp312-cp312-linux_x86_64.whl
https://djl-ai.s3.us-east-1.amazonaws.com/publish/vllm/vllm-0.16.1.dev6%2Bg369fca226-cp312-cp312-linux_x86_64.whl
lmcache
autoawq
Loading