https://pypi.org/project/llama-dyno/ Recent updates to the Python Package Index for llama-dyno en https://pypi.org/project/llama-dyno/1.5.0/ Auto-tune and benchmark llama.cpp / ik_llama.cpp inference on NVIDIA, AMD (ROCm), and Apple Silicon GPUs lachy@flowdesk.systems Sat, 18 Jul 2026 10:38:15 GMT https://pypi.org/project/llama-dyno/1.4.0/ Auto-tune and benchmark llama.cpp / ik_llama.cpp inference on NVIDIA, AMD (ROCm), and Apple Silicon GPUs lachy@flowdesk.systems Sat, 18 Jul 2026 10:29:34 GMT https://pypi.org/project/llama-dyno/1.3.0/ Auto-tune and benchmark llama.cpp / ik_llama.cpp inference on NVIDIA and Apple Silicon GPUs lachy@flowdesk.systems Sat, 18 Jul 2026 10:26:27 GMT https://pypi.org/project/llama-dyno/1.2.0/ Auto-tune and benchmark llama.cpp / ik_llama.cpp inference on NVIDIA and Apple Silicon GPUs lachy@flowdesk.systems Sat, 18 Jul 2026 10:10:39 GMT https://pypi.org/project/llama-dyno/1.1.0/ Auto-tune and benchmark llama.cpp / ik_llama.cpp inference on NVIDIA GPUs lachy@flowdesk.systems Sat, 18 Jul 2026 09:43:40 GMT https://pypi.org/project/llama-dyno/1.0.2/ Auto-tune and benchmark llama.cpp / ik_llama.cpp inference on NVIDIA GPUs lachy@flowdesk.systems Sat, 18 Jul 2026 08:20:48 GMT