Baseten is an AI infrastructure platform. We combine applied performance research, distributed multi-cloud infrastructure, and developer tooling to run models of all modalities in production.
Get started:
HuggingFace conversion and training library for Megatron-based models
Ongoing research training transformer models at scale
A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
A unified library of state-of-the-art model optimization techniques such as quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM or TensorRT to optimize inference speed on NVIDIA GPUs.
Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serving systems.
Renderer for the harmony response format to be used with gpt-oss
Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)
Loading…
Loading…
