3Show HN: Binfer, an experimental LLM inference engine in TypeScript and CUDA (opens in new tab)(github.com)1brrrrrm3mo ago0
5Bitwise Consistent On-Policy Reinforcement Learning with VLLM and TorchTitan (opens in new tab)(blog.vllm.ai)1brrrrrm4mo ago0
6Should we apply old-school multi-core scheduling to GPUs? (opens in new tab)(jott.live)4brrrrrm4mo ago0
7Show HN: GT: experimental multiplexed distributed tensor framework (opens in new tab)(github.com)4brrrrrm4mo ago0
8GT – Experimental multiplexing tensor framework for distributed GPU computing (opens in new tab)(github.com)30brrrrrm4mo ago1
9MFU Is Poorly Approximating Billions of Dollars in Compute (opens in new tab)(jott.live)4brrrrrm6mo ago0
11SWE-bench verified agents may look at future repository state (opens in new tab)(github.com)4brrrrrm6mo ago0
