R9V Update: Created and adopted KVA projections based on Deepseek V4.1 Flash + HySparse2/MiMo-V3 for Qwen3.8 Flash Next. This is a game changer for models that don't natively implement it. 1.45-1.85x speedup in prefill to 3k+ at a small deficit to perplexity. [2x R9700, 128GB DDR5]
英文标题：R9V Update: Created and adopted KVA projections based on Deepseek V4.1 Flash + HySparse2/MiMo-V3 for Qwen3.8 Flash Next. This is a game changer for models that don't natively implement it. 1.45-1.85x speedup in prefill to 3k+ at a small deficit to perplexity. [2x R9700, 128GB DDR5]
Here's my *first* implementation of KVA projectors on QFN (just the uncensored model for now) the highlights are basically as follows for using the projectors at each different layer: Starting at layer 12, prompt processing speeds up 1.85x [1700 t/s -> 3150 t/s] at the tradeoff of increasing p
中文
Here's my *first* implementation of KVA projectors on QFN (just the uncensored model for now) the highlights are basically as follows for using the projectors at each different layer: Starting at layer 12, prompt processing speeds up 1.85x [1700 t/s -> 3150 t/s] at the tradeoff of increasing p
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
Here's my *first* implementation of KVA projectors on QFN (just the uncensored model for now) the highlights are basically as follows for using the projectors at each different layer: Starting at layer 12, prompt processing speeds up 1.85x [1700 t/s -> 3150 t/s] at the tradeoff of increasing p