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, 04:30 UTC
[Bugfix] Fix issues in CPU build Dockerfile. Fixes #9182 (#11435)
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
Yuan Tang committed
Dec 24, 2024 at 11:53 UTC
409475a827795000301f0d27582befab0563888b
2 files changed
+10
-6
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
30
ARG PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu"
31
ENV PIP_EXTRA_INDEX_URL=${PIP_EXTRA_INDEX_URL}
32
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
42
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
+7
-3
@@ -455,9 +455,13 @@ def get_gaudi_sw_version():
455
456
457
def get_vllm_version() -> str:
458
- version = get_version(
459
- write_to="vllm/_version.py", # TODO: move this to pyproject.toml
460
- )
458
+ # TODO: Revisit this temporary approach: https://github.com/vllm-project/vllm/issues/9182#issuecomment-2404860236
459
+ try:
460
+ version = get_version(
461
+ write_to="vllm/_version.py", # TODO: move this to pyproject.toml
462
+ )
463
+ except LookupError:
464
+ version = "0.0.0"
465
466
sep = "+" if "+" not in version else "." # dev versions might contain +
467