In a controlled comparison by Grant Herlein, the minimalist C-based agent hax completed a frozen coding task 1.82x faster than the full-featured oh-my-pi (omp) agent, with median times of 45.7 minutes…
A developer achieved ~28 tok/s single-stream decode of DeepSeek-V4-Flash (284B MoE) on a single RTX 5090 with dual Xeon Gold 6138 CPUs using a CPU-offloaded expert recipe. The setup uses ktransformers…
Wafer served GLM5.2 on AMD MI355X GPUs at 2626 tokens per second per node with over 2x lower cost than NVIDIA Blackwell, achieving 213 tok/s single stream. The company used MXFP4 quantization via AMD …
A developer launched an unlimited LLM provider for $6/month using 4x RTX 3090s after a failed launch on AMD MI300x hardware. Despite initial bugs and hardware issues, the service gained traction with …
A developer has released LLMhop, a stateless HTTP router that directs OpenAI-compatible API requests to the appropriate LLM inference backend based on the model name in the request body. The single-bi…