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, 19:30 UTC
bump version to v0.5.4 (#7139)
Simon Mo committed
Aug 5, 2024 at 14:39 UTC
4db5176d9758b720b05460c50ace3c01026eb158
2 files changed
+2
-2
docs/source/getting_started/installation.rst
+1
-1
@@ -48,7 +48,7 @@ You can install vLLM using pip:
48
49
.. code-block:: console
50
51
- $ export VLLM_VERSION=0.5.2 # vLLM's main branch version is currently set to latest released tag
51
+ $ export VLLM_VERSION=0.5.4 # vLLM's main branch version is currently set to latest released tag
52
$ pip install https://vllm-wheels.s3.us-west-2.amazonaws.com/nightly/vllm-${VLLM_VERSION}-cp38-abi3-manylinux1_x86_64.whl
53
$ # You can also access a specific commit
54
$ # export VLLM_COMMIT=...
vllm/version.py
+1
-1
@@ -9,4 +9,4 @@ except Exception as e:
9
stacklevel=2)
10
__commit__ = "COMMIT_HASH_PLACEHOLDER"
11
12
-__version__ = "0.5.3.post1"
12
+__version__ = "0.5.4"