Skip to content
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

Jump to bottom

fix: enable logprobs during spec decoding by default #131

Merged
merged 1 commit into from
Aug 21, 2024
Merged

fix: enable logprobs during spec decoding by default #131

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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: 8 additions & 2 deletions Dockerfile.ubi
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -181,7 +181,6 @@ RUN --mount=type=cache,target=/root/.cache/pip \
uv pip install https://github.com/flashinfer-ai/flashinfer/releases/download/v0.1.2/flashinfer-0.1.2+cu121torch2.4-cp311-cp311-linux_x86_64.whl

ENV HF_HUB_OFFLINE=1 \
PORT=8000 \
HOME=/home/vllm \
# Allow requested max length to exceed what is extracted from the
# config.json
Expand All @@ -208,6 +207,13 @@ USER root
RUN --mount=type=cache,target=/root/.cache/pip \
pip install vllm-tgis-adapter==0.3.0

ENV GRPC_PORT=8033
ENV GRPC_PORT=8033 \
PORT=8000 \
# As an optimization, vLLM disables logprobs when using spec decoding by
# default, but this would be unexpected to users of a hosted model that
# happens to have spec decoding
# see: https://github.com/vllm-project/vllm/pull/6485
DISABLE_LOGPROBS_DURING_SPEC_DECODING=false

USER 2000
ENTRYPOINT ["python3", "-m", "vllm_tgis_adapter", "--uvicorn-log-level=warning"]
Loading