qlabs-eng/slowrun

Infinite compute language modeling benchmark

View on index · View in 3D Map

Related repos

• High performance serving for language models
• Benchmark for jailbreaking language models
• CPU simulation for flaky-free benchmarks
• micro-benchmarks for C++ performance tradeoffs
• Library for running and serving large language models
• Portable vendor-neutral parallel computing in Julia
• quick Linux server benchmark with cpu, disk, and network tests
• massively parallel programming language for GPUs and CPUs
• Train language models under 16MB
• open-source large language models for chat, code, and multilingual tasks