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 15, 16:00 UTC
[Misc] remove unused script (#15746)
Signed-off-by: reidliu41 <reid201711@gmail.com> Co-authored-by: reidliu41 <reid201711@gmail.com>
Reid committed
Apr 1, 2025 at 21:58 UTC
2e45bd29fe738265931ed2565fc6b1d9aac0521a
1 file changed
-16
python_only_dev.py
deleted
-16
@@ -1,16 +0,0 @@
1
-# SPDX-License-Identifier: Apache-2.0
2
-
3
-msg = """Old style python only build (without compilation) is deprecated, please check https://docs.vllm.ai/en/latest/getting_started/installation.html#python-only-build-without-compilation for the new way to do python only build (without compilation).
4
-
5
-TL;DR:
6
-
7
-VLLM_USE_PRECOMPILED=1 pip install -e .
8
-
9
-or
10
-
11
-export VLLM_COMMIT=33f460b17a54acb3b6cc0b03f4a17876cff5eafd # use full commit hash from the main branch
12
-export VLLM_PRECOMPILED_WHEEL_LOCATION=https://wheels.vllm.ai/${VLLM_COMMIT}/vllm-1.0.0.dev-cp38-abi3-manylinux1_x86_64.whl
13
-pip install -e .
14
-""" # noqa
15
-
16
-print(msg)