Viewing profile — aarnphm

Hi srameshc, the core of BentoML is still considered MLOps. A lot of our customers are pretty much MLOps users. However, LLMOps seem like a natural progression of the product, give…

Thanks for the recommendation, I'm actually working on something similar for this part of the docs (I'm also working at BentoML).

You can pretty much make the same argument about Docker. Docker abstracts away runc, runc abstract away cgroup. I don't think calling it abstraction is correct. OneDiffusion is des…

Currently on main, 8bit and 4bit quant is supported One can simply do ```openllm start falcon --model-id tiiuae/falcon-40b-instruct --quantize int4``` Beware that there is no free …

Hi there, 8bit and 4bit is currently supported on main. GPTQ is working in progress, as well as GGML

Hi all, I'm the main maintainer from the OpenLLM team here. I'm actively developing the fine-tuning feature and will release a PR soon enough. Stay tuned. In the meanwhile, the bes…

Again?? I definitely have to try out BentoML then to see what the hype is about!!

BentoML is an amazing tool that allows you to quickly and easily deploy your machine learning models as APIs. It is extremely user-friendly and easy to use, and the results are ama…