vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
amdblackwellcudadeepseekdeepseek-v3gptgpt-ossinferencekimillama
上榜紀錄 Trending history
- 2026-10-22 每日 Daily #2
- 2026-10-21 每日 Daily #15
A high-throughput and memory-efficient inference and serving engine for LLMs