Atlas Inference is a pure Rust & CUDA/ROCm LLM inference engine hand-tuned for edge hardware like NVIDIA DGX Spark and AMD Strix Halo. Zero Python, zero PyTorch, a single compact binary with gate-enforced baselines and MLPerf v6.1 benchmarks.
Website: https://atlasinference.dev
Atlas Inference is a pure Rust & CUDA/ROCm LLM inference engine hand-tuned for edge hardware like NVIDIA DGX Spark and AMD Strix Halo. Zero Python, zero PyTorch, a single compact binary with gate-e…
Atlas Inference is a dependency free lightweight inference engine meant to run LLMs on YOUR compute seamlessly. Supports GB10 and Strix Halo at the moment, hoping to expand to more!
Atlas Inference is a pure Rust & CUDA/ROCm LLM inference engine hand-tuned for edge hardware like NVIDIA DGX Spark and AMD Strix Halo. Zero Python, zero PyTorch, a single compact binary with gate-enforced baselines and MLPerf v6.1 benchmarks.
This organization has no public members. You must be a member to see who’s a part of this organization.
Loading…
Loading…
