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 17, 03:00 UTC
[CI/Build] 0.4.0.post1, fix sm 7.0/7.5 binary (#3803)
youkaichao committed
Apr 2, 2024 at 12:57 UTC
a3c226e7eb19b976a937e745f3867eb05f809278
1 file changed
+1
-1
vllm/__init__.py
+1
-1
@@ -8,7 +8,7 @@ from vllm.entrypoints.llm import LLM
8
from vllm.outputs import CompletionOutput, RequestOutput
9
from vllm.sampling_params import SamplingParams
10
11
-__version__ = "0.4.0"
11
+__version__ = "0.4.0.post1"
12
13
__all__ = [
14
"LLM",