Faculty, School of Computer Sciences, NISER
ପାଠକ-ଏଫ, ସଂଗଣକ ବିଜ୍ଞାନ ବିଦ୍ୟାଳୟ, ନାଇଜର
| Time | Session | Topic |
|---|---|---|
| 10:30 AM - 12:30 PM | Session 1 | LLM Inference, LLM Inference Measurement, LLM Inference Difference from other Inference, Chunked Prefill and KV caching, Attention Mechanism, TRT-LLM+Triton, TRT LLM features |
| Session 2 | Run:AI software platform, Using run:ai to do LLM inference | |
| 2:30 PM - 5:00 PM | Session 3 | Discussion on run:ai to automate allocation of computing resources for AI infrastructure |
| Session 4 | Exploring multimodal models in run:ai from NVIDIA | |
| Session 5 | Run PEFT in runai to finetune a large language model using NVIDIA frameworks |