Popular repositories Loading

1. vllm-serving-bench vllm-serving-bench Public

   Benchmark OpenAI-compatible vLLM serving endpoints

   Python 3

2. llm-ddp-lora-bench llm-ddp-lora-bench Public

   基于 Qwen2.5-0.5B 的 LoRA 微调训练系统实验，对比单卡、DDP、FSDP 下的 step time、tokens/s、显存占用与多 GPU 扩展效率。 仓库名：

   Python 1

3. qwen-kernel-lab qwen-kernel-lab Public

   Python 1

4. qwen-inference-lab qwen-inference-lab Public

   Lightweight Qwen inference engine with adaptive chunked prefill scheduling, paged KV cache, and CPU-tested scheduling policies.

   Python

5. guidellm guidellm Public

   Forked from vllm-project/guidellm

   Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs

   Python

6. vllm vllm Public

   Forked from vllm-project/vllm

   A high-throughput and memory-efficient inference and serving engine for LLMs

   Python