Hacker Newsnew | past | comments | ask | show | jobs | submit | venkat_2811's submissionslogin
1.
ns scale ultra-low-latency fabric over shm and MMAP for IPC (crates.io)
2 points by venkat_2811 5 days ago | past | discuss
2.
Show HN: Nvidia's CUDA libraries are generic and not optimized for LLM inference (github.com/venkat2811)
1 point by venkat_2811 4 months ago | past | 1 comment
3.
I Beat Nvidia NCCL by 2.4x (venkat-systems.bearblog.dev)
2 points by venkat_2811 4 months ago | past | 2 comments

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: