8-9 t/s并没有完全发挥8060S的潜力，llama.cpp的llama-server有一个小问题导致server配speculative decoding时性能欠佳（与具体硬件无关）：https://github.com/ggml-org/llama.cpp/issues/12968
动手简单修一下这个问题之后Qwen 2.5 72B iq4_xs + 1.5B draft在acceptance rate理想时可达到10-12 t/s左右
https://github.com/hjc4869/llama.cpp/commit/0b32f64ffbe973e99e0dc7097be31d4d966d476e
BY David's random thoughts
Telegram is a cloud-based instant messaging service that has been making rounds as a popular option for those who wish to keep their messages secure. Telegram boasts a collection of different features, but it’s best known for its ability to secure messages and media by encrypting them during transit; this prevents third-parties from snooping on messages easily. Let’s take a look at what Telegram can do and why you might want to use it.
However, analysts are positive on the stock now. “We have seen a huge downside movement in the stock due to the central electricity regulatory commission’s (CERC) order that seems to be negative from 2014-15 onwards but we cannot take a linear negative view on the stock and further downside movement on the stock is unlikely. Currently stock is underpriced. Investors can bet on it for a longer horizon," said Vivek Gupta, director research at CapitalVia Global Research.
David& 39;s random thoughts from it