Model fails to load when chat template uses HuggingFace generation tags

Called `model.embed` generates INFO messages for each input

Multiple calls to create_chat_completion() fail with "llama_decode: failed to decode, ret = -1"

Add riscv64 (linux_riscv64) wheel to PyPI releases

📋 Documentation Enhancement Suggestion

Link https://abetlen.github.io/llama-cpp-python/whl/cu125 returns 404 Not Found.

Shopping

Shopping

[Deployment Issue] Installation deadlock on Hugging Face Spaces (CPU): Wheels fail (musl/glibc mismatch) & Source builds timeout

Sonu Kumar