Search results for "BIT"
Today
02:32

Google Releases TurboQuant Algorithm: 3-bit KV Cache Quantization With No Accuracy Loss, Inference Speed Boosted Up to 8x

Google Research has released the TurboQuant algorithm, which can compress the KV cache of large language models to 3 bits, reducing memory usage by at least 6 times while maintaining accuracy without requiring training. The algorithm optimizes traditional quantization through two sub-algorithms: PolarQuant and QJL. Testing shows excellent performance across multiple long-context benchmarks.
More
13:08

Tether introduces the BitNet LoRA framework, supporting large model training on mobile devices

Gate News report: On March 17, Tether's QVAC Fabric launched the world's first cross-platform LoRA fine-tuning framework for Microsoft BitNet (1-bit LLM), significantly lowering the VRAM and computational thresholds for large model training. The framework supports LoRA fine-tuning and inference acceleration on Intel, AMD, Apple Silicon M series, and mobile GPUs (including Adreno, Mali, and Apple Bionic).
More
09:16

Bit Digital's Ethereum holdings increase to 155,000 coins, with a staking rate of approximately 89%

Gate News Report, March 6 — The fifth-largest Ethereum treasury company, Bit Digital (BTBT), released an holdings update. As of February 28, 2026, the company's Ethereum holdings increased to 155,434.4 ETH, valued at approximately $305.4 million, with an average purchase price of $3,045. By the end of February, BTBT had staked a total of 138,269.6 ETH, accounting for about 89% of its total holdings, generating approximately 313.9 ETH in staking rewards.
More
ETH-2,97%