Frank Mai thxCode

• Seal

• ShenZhen, GuangDong

Organizations

Pinned Loading

1. Performance-optimized AI inference on your GPUs. Unlock superior throughput by selecting and tuning engines like vLLM or SGLang.

   Python 4.7k 477

2. LM inference server implementation based on *.cpp.

   C++ 296 28

3. Review/Check GGUF files and estimate the memory usage and maximum tokens per second.

   Go 250 24

4. Deliver LLMs of GGUF format via Dockerfile.

   Go 15 5

5. Available Terraform Provider network mirroring service.

   Go 48 7

6. Patch Terraform Resource As Your Mind.

   Go 15