# Fast Inference

Wafer-scale inference at thousands of tokens per second

Cerebras Inference serves open-weight LLMs like Llama, Qwen, and GPT-OSS on wafer-scale CS-3 chips through an OpenAI-compatible API, benchmarking between 1,800 and 2,600 output tokens per second on Llama 3.1 8B and several hundred on 70B models. A free tier offers one million tokens per day with no credit card, while paid pay-per-token pricing starts at $0.04 per million tokens for the smaller Llama models.

Heterogeneous CPU-GPU inference and SFT for large MoE models

Open-source framework for running and fine-tuning large Mixture-of-Experts models with heterogeneous CPU-GPU execution, optimized kernels, limited VRAM and SGLang or LLaMA-Factory integrations.

Open-source toolkit for quantizing, deploying, and serving LLMs and vision-language models

LMDeploy is an Apache-2.0 toolkit for self-hosting LLM and vision-language model inference with TurboMind and PyTorch engines. It combines continuous batching, blocked KV cache, tensor parallelism, AWQ and KV-cache quantization with OpenAI-compatible APIs, multi-GPU distribution, offline pipelines, and production metrics.

Edge AI deployment SDK for heterogeneous SoCs

Roofline AI is a contact-sales edge AI deployment toolkit built around an MLIR- and IREE-based compiler. Its SDK compiles models ahead of time, a lightweight C runtime executes them across CPUs, GPUs, and NPUs, and a performance dashboard tracks latency, throughput, memory use, and model coverage across devices.