[TPU] Support tensor parallelism in async llm engine (#6891)
This commit is contained in:
@@ -12,6 +12,9 @@ RUN pip install "numpy<2"
|
||||
RUN pip install torch_xla[tpu] -f https://storage.googleapis.com/libtpu-releases/index.html
|
||||
RUN pip install torch_xla[pallas] -f https://storage.googleapis.com/jax-releases/jax_nightly_releases.html -f https://storage.googleapis.com/jax-releases/jaxlib_nightly_releases.html
|
||||
|
||||
# Fix FastAPI dependence
|
||||
RUN pip install "starlette<0.38.0"
|
||||
|
||||
# Build vLLM.
|
||||
COPY . /workspace/vllm
|
||||
ENV VLLM_TARGET_DEVICE="tpu"
|
||||
|
||||
Reference in New Issue
Block a user