anodyine/vllm-omni

0 Fork 0

Files

T

History

tzhouam f24273dc03 Update vLLM version to 0.16.0 in quickstart and CUDA installation documentation, and adjust parameters in multimodal generation script for improved performance. Refactor request logging in serving_chat.py for better input tracking.

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>

2026-02-13 09:50:11 +00:00

..

Update vLLM version to 0.16.0 in quickstart and CUDA installation documentation, and adjust parameters in multimodal generation script for improved performance. Refactor request logging in serving_chat.py for better input tracking.

2026-02-13 09:50:11 +00:00

[Hardware] [Feat] Setup platform dependent package installation (#1046 )

2026-02-05 21:47:41 +08:00

.nav.yml

[Docs] optimize and supplement docs system (#86 )

2025-11-28 11:03:52 +08:00

gpu.md

[Hardware] [Feat] Setup platform dependent package installation (#1046 )

2026-02-05 21:47:41 +08:00

npu.md

[NPU] Update Dockerfile and docs for v0.14.0 (#671 )

2026-02-04 15:10:50 +08:00

python_env_setup.inc.md

[Docs] optimize and supplement docs system (#86 )

2025-11-28 11:03:52 +08:00

README.md

[Doc] [ROCm]: Document the steps to run vLLM Omni on ROCm (#144 )

2025-12-11 01:42:05 -08:00

README.md

Installation

vLLM-Omni supports the following hardware platforms:

GPU
- NVIDIA CUDA
- AMD ROCm
NPU