Open Issues Need Help
View All on GitHub Verify first-time wheel installation and onboarding about 12 hours ago
help wanted
Reproducible local llama.cpp deployment benchmarks, resource measurements and failure evidence for consumer GPUs.
Python
#benchmarking#consumer-gpu#llama-cpp#local-llm
Collect independent GPU and Linux reproductions about 12 hours ago
help wanted
Reproducible local llama.cpp deployment benchmarks, resource measurements and failure evidence for consumer GPUs.
Python
#benchmarking#consumer-gpu#llama-cpp#local-llm