A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 02:00 UTC
[Bugfix] Fix issues in CPU build Dockerfile (#12135)
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
Yuan Tang committed
Jan 16, 2025 at 23:54 UTC
b8bfa46a18abe0bf9f48a29e1e8dd2bc1a79af98
2 files changed
+6
-10
Dockerfile.cpu
+3
-3
@@ -26,10 +26,10 @@ RUN pip install intel_extension_for_pytorch==2.5.0
26
27
WORKDIR /workspace
28
29
-COPY requirements-build.txt requirements-build.txt
29
ARG PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu"
30
ENV PIP_EXTRA_INDEX_URL=${PIP_EXTRA_INDEX_URL}
31
RUN --mount=type=cache,target=/root/.cache/pip \
32
+ --mount=type=bind,src=requirements-build.txt,target=requirements-build.txt \
33
pip install --upgrade pip && \
34
pip install -r requirements-build.txt
35
@@ -37,9 +37,9 @@ FROM cpu-test-1 AS build
37
38
WORKDIR /workspace/vllm
39
40
-COPY requirements-common.txt requirements-common.txt
41
-COPY requirements-cpu.txt requirements-cpu.txt
40
RUN --mount=type=cache,target=/root/.cache/pip \
41
+ --mount=type=bind,src=requirements-common.txt,target=requirements-common.txt \
42
+ --mount=type=bind,src=requirements-cpu.txt,target=requirements-cpu.txt \
43
pip install -v -r requirements-cpu.txt
44
45
COPY . .
setup.py
+3
-7
@@ -472,13 +472,9 @@ def get_gaudi_sw_version():
472
473
474
def get_vllm_version() -> str:
475
- # TODO: Revisit this temporary approach: https://github.com/vllm-project/vllm/issues/9182#issuecomment-2404860236
476
- try:
477
- version = get_version(
478
- write_to="vllm/_version.py", # TODO: move this to pyproject.toml
479
- )
480
- except LookupError:
481
- version = "0.0.0"
475
+ version = get_version(
476
+ write_to="vllm/_version.py", # TODO: move this to pyproject.toml
477
+ )
478
479
sep = "+" if "+" not in version else "." # dev versions might contain +
480