[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

@ArtiIntelligent "@adrgrondin @LocallyAIApp Can we use it to talk to a custom LLM that runs on our own server This would be following the OpenAI spec"
X Link @ArtiIntelligent 2025-10-30T18:21Z XXX followers, XXX engagements

"@rasbt X. Make sure you are using the latest docker image from here and serve using tensor-rt: They have optimized kernels for the spark X. Try to run the FP4 optimized variants of your model from nvidia. Also run gpt-oss-120B which gets 30+ tokens per second"
X Link @ArtiIntelligent 2025-10-31T12:44Z XXX followers, XXX engagements