Viewing profile — venkat_2811

while i'm a fan of wafer's work, 1024 input token length is not a great benchmark anymore, that number is useful only at 1-4x single node a100 / h100 at various concurrency levels

ai agents failing silently or just lying is a big problem Steadwing and openalerts save a lot of headache for sure ! congrats on the launch !

With so much improvements in LLM Inference Kernels, Inter-GPU comms are becoming the bottleneck. Introducing my project YALI - Yet Another Low-Latency Implementation. A custom CUDA…

Wisdom from CPU land translate well to GPUs. Static Scheduling, Pre-fetching, 3-Stage Double-Buffering, Pre-allocation & memory ordering in custom CUDA kernel helps outperform NVID…

100% OSS, MIT License. YALI - Yet Another Low-Latency Implementation. Achieves 80-85% Speed-of-Light SW efficiency by using ultra low-latency primitives for p2p all_reduce_sum comm…