Search Results: "llama_cpp"

Found 5 articles

Regulation

Trillion-Parameter LLM on an AMD Ryzen™ AI Max+ Cluster

3/1/2026
GNOME's Newelle 1.2 Brings Local LLM Execution and Command Execution to the Desktop
AI

GNOME's Newelle 1.2 Brings Local LLM Execution and Command Execution to the Desktop

1/24/2026
ZLUDA Achieves Full Llama.cpp Compatibility, Enhances Windows Support for AMD CUDA Acceleration
Hardware

ZLUDA Achieves Full Llama.cpp Compatibility, Enhances Windows Support for AMD CUDA Acceleration

1/14/2026
Experiment Reveals Bizarre Outputs When Sampling LLaMA at Negative Temperatures
LLMs

Experiment Reveals Bizarre Outputs When Sampling LLaMA at Negative Temperatures

1/12/2026
AMD Matrix Cores Supercharge Llama.cpp: MFMA and Stream-K Unlock 9.5K Tokens/sec on MI300X
Hardware

AMD Matrix Cores Supercharge Llama.cpp: MFMA and Stream-K Unlock 9.5K Tokens/sec on MI300X

The CDNA 3 Breakthrough A landmark pull request in llama.cpp has fundamentally transformed AMD GPU performance for l...

7/28/2025