@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 81653d9688
Fork 0

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.