av_conk
Re:Llama.cpp supports Vulkan. why doesn't Ollama?
on Friday January 31, 2025 @09:58AM (#42888302)
I tried using ollama because I couldn't get ROCm working on my system with llama-cpp. Ollama bundles the ROCm libraries for you. I got around 50 tokens per second with that setup.
I tried llama-cpp with the Vulkan backend and doubled the amount of tokens per second. I was under the impression ROCm is superior to Vulkan, so I was confused about the result.
In any case, I've stuck with llama-cpp.
Re:How to pack ternary numbers in 8-bit bytes
on Thursday December 05, 2024 @01:19PM (#42330847)
There's emerging work on using the quantum analogue for trits (qutrits) in quantum computing.
They are more robust to certain errors.
Re:We live in the age of the bullshitter
on Tuesday January 10, 2023 @09:11AM (#34325054)
I've definitely caught myself bullshitting in the past. It may be difficult at first, but saying "I don't know" is very important.
Re:Glassdoor not so anonymous
on Monday July 18, 2022 @10:08PM (#32146707)
You can use a firefox extension to bypass that popup as well as other paywalls.
Re:OCaml Multicore merged upstream
on Monday January 10, 2022 @12:25PM (#29878195)
Real World OCaml (https://dev.realworldocaml.org/) is a great one.
Re:GitHub Copilot
on Tuesday June 29, 2021 @11:17AM (#27677055)
From the FAQ:
"Not yet. For now, we’re focused on delivering the best experience in Visual Studio Code only."
I do hope they feature others at a later date, especially since they are planning to develop a commercial version.