SuspiciousCarrot78@aussie.zone to Selfhosted@lemmy.worldEnglish · 25 days agoDo you host your own AI?message-squaremessage-square205linkfedilinkarrow-up1185file-text
arrow-up1185message-squareDo you host your own AI?SuspiciousCarrot78@aussie.zone to Selfhosted@lemmy.worldEnglish · 25 days agomessage-square205linkfedilinkfile-text
minus-squareSuspiciousCarrot78@aussie.zoneOPlinkfedilinkEnglisharrow-up13·24 days agoLlama.cpp or death!
minus-squareBlackLaZoR@lemmy.worldlinkfedilinkEnglisharrow-up2·23 days agoI use LMStudio, because it has quality of life improvements like nice GUI and huggingface search engine. Also they have Vulkan backend that at least on 7900XTX is ~10% faster than rocm (on LLama 3 8b Q4_0 it gets 115Tokens/s vs 105 on rocm)
minus-squarebrucethemoose@lemmy.worldlinkfedilinkEnglisharrow-up3·24 days agoOr exllama! Vllm, sglang, Lorax. Koboldcpp, Aphrodite, text-generation-webui, LM Studio, powerinfer, ktransformers, mlc-LLM, really whatever floats your boat. Just not ollama, specifically.
Llama.cpp or death!
deleted by creator
I use LMStudio, because it has quality of life improvements like nice GUI and huggingface search engine. Also they have Vulkan backend that at least on 7900XTX is ~10% faster than rocm (on LLama 3 8b Q4_0 it gets 115Tokens/s vs 105 on rocm)
Or exllama! Vllm, sglang, Lorax. Koboldcpp, Aphrodite, text-generation-webui, LM Studio, powerinfer, ktransformers, mlc-LLM, really whatever floats your boat. Just not ollama, specifically.