Show HN: Binfer, an experimental LLM inference engine in TypeScript and CUDAgithub.com·1 pts·brrrrrm·0
Bitwise Consistent On-Policy Reinforcement Learning with VLLM and TorchTitanblog.vllm.ai·1 pts·brrrrrm·0
GT – Experimental multiplexing tensor framework for distributed GPU computinggithub.com·30 pts·brrrrrm·1