Researcher Praises Together's Torch Compile vs Megakernel Tradeoff Study
simran_s_arora · x · 2026-11-17
Weili amplifies and comments on research from the Together Compute team (Simran Arora, Dylan Lim, Reyna Abhyankar) that investigated tradeoffs between Torch Compile and Megakernels, leading to Together Compile.
The comment stresses investigating both sides, citing the authors' note about a Hazy lab tradition of comparing both approaches, tracing back to S4 no-attention vs FlashAttention.
More from Infra
- Together Compute Deleted Its Megakernels: Whole-Model Kernels Overcomplicate Optimization — simran_s_arora · 2026-11-17
- Kalshi to Launch Stock Trading and AI Compute Futures, Reportedly Raising at $65B Valuation — nima_owji · 2026-11-17
- SpaceX uniquely owns the ride to orbit, the global network, and the AI computers at once — ccerrato147 · 2026-11-17
- Nvidia earnings could be good for NVDA but bad for the rest of the AI trade — pdamodaran · 2026-11-17
- TensorFold Runs Local LLMs at 874 tok/s With Native Metal/CUDA Inference — AIFlow_ML · 2026-11-17
- AMD's Dan McNamara: billions of AI agents will reshape CPU demand, Venice chips now shipping — firstadopter · 2026-11-17