agentionai/strix-halo-bench-workloads download history
agentionai/strix-halo-bench-workloads is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 80 times (39 in the last 7 days), and 156 times in total. It ranks #179,505 among datasets by monthly downloads.
Strix Halo llama.cpp benchmark workloads Fixed prompt sets for measuring real-world llama-server performance of strix-llama.cpp on AMD Strix Halo (Ryzen AI Max+, gfx1151): single-stream decode and prompt throughput, time to first token, and speculative-decoding (MTP) acceptance. Resul
Open agentionai/strix-halo-bench-workloads on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.