TurboQuant

Articles tagged with TurboQuant

5 articles

All Critical (9-10) Important (7-8) Notable (5-6) Logged (1-4) 5 matches

Editorial illustration for: Google's TurboQuant Compresses AI Memory Cache Without Accuracy Loss

Google TurboQuant Compresses LLM KV Cache Without Accuracy Loss

7/10 4 min read 2 months ago

Editorial illustration for: Developer Patches llama.cpp with Google TurboQuant to Run Qwen 3.5-9B on MacBook Air

Developer Runs Qwen 3.5-9B on MacBook Air M4 via TurboQuant-Patched llama.cpp

7/10 4 min read 2 months ago

Editorial illustration for: TurboQuant Optimization Achieves 22.8 Percent Decode Speedup in llama.cpp by Skipping Redundant K

TurboQuant Optimization Achieves 22.8 Percent Decode Speedup in llama.cpp by Skipping Redundant KV Dequantization

8/10 3 min read 2 months ago

Editorial illustration for: Google Unveils TurboQuant Algorithm That Cuts AI Memory Use by 6x and Costs by 50 Percent

Google Unveils TurboQuant Algorithm That Cuts AI Memory Use by 6x and Costs by 50 Percent

8/10 2 min read 2 months ago

Editorial illustration for: Google Research Unveils TurboQuant Compression for AI Models

Google Research Publishes TurboQuant Two-Stage LLM Compression System

8/10 4 min read 2 months ago

📬 Get AI news daily → Subscribe Free