Search
Media & Creative · CUDA · By vllm-project
1 skill found.
Skills
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Integrate a new text-to-speech model into vLLM-Omni from HuggingFace reference implementation through production-ready serving with streaming and CUDA graph acceleration. | vllm-project/ | 7.1k | — | ~8.7k | Automated safety check: Pass | Apache-2.0 | today |
