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, 04:15 UTC
[Hotfix] [Debug] test_openai_server.py::test_guided_regex_completion (#3383)
Simon Mo committed
Mar 13, 2024 at 17:02 UTC
81653d968842d2ec51b2642b6b5d83786271f9af
2 files changed
+2
-2
.buildkite/test-pipeline.yaml
+1
-1
@@ -13,7 +13,7 @@ steps:
13
14
- label: Basic Correctness Test
15
command: pytest -v -s --forked basic_correctness
16
-
16
+
17
- label: Core Test
18
command: pytest -v -s core
19
requirements.txt
+1
-1
@@ -12,5 +12,5 @@ pydantic >= 2.0 # Required for OpenAI server.
12
prometheus_client >= 0.18.0
13
pynvml == 11.5.0
14
triton >= 2.1.0
15
-outlines >= 0.0.27
15
+outlines == 0.0.34
16
cupy-cuda12x == 12.1.0 # Required for CUDA graphs. CUDA 11.8 users should install cupy-cuda11x instead.