@Modular: People ask what our secret is when they see our performance numbers. Brendan Hansknecht, AI Performance Engineering Man…
Summary
Brendan Hansknecht from Modular explains that their high performance numbers stem from treating performance as a full-stack problem, rather than relying on piecemeal components in production.
View Cached Full Text
Cached at: 09/04/26, 12:19 AM
People ask what our secret is when they see our performance numbers.
Brendan Hansknecht, AI Performance Engineering Manager, on why performance is a full-stack problem, and why gluing together someone else’s kernels, tokenizers, and schedulers doesn’t work in production:
@Modular: People ask what our secret is when they see our performance numbers. Brendan Hansknecht, AI Performance Engineering Man…
Channel: @Modular Source: https://www.youtube.com/watch?v=J_ezNJ6eyHk
Similar Articles
@Modular: AI teams face two problems at once: compute is hard to get, and the hardware they can get is splintering across a growi…
Modular's Chief Scientist Abdul Dakkak discusses at AI Engineer World's Fair 2026 why the company rebuilt its inference stack from scratch to run efficiently across a fragmented landscape of chips and accelerators.
@AIatAMD: AI is changing how we build software. Curiosity still matters. @clattner_llvm, CEO and Co-founder of @Modular, shares h…
Chris Lattner, CEO and Co-founder of Modular, shares his perspective on how AI is changing software development and why curiosity still matters.
@Modular: Modular is live on @ArtificialAnlys with 3x faster image generation than the competition. MAX inference serving @bfl_ai…
Modular's MAX inference serving achieves 3x faster image generation for FLUX.2-dev than competitors, as per Artificial Analysis benchmarks.
@Modular: Modular's price-performance on @Zai_org's GLM-5.2 (Non-reasoning) lands right on the Pareto frontier in @ArtificialAnly…
Modular demonstrates strong price-performance on Zai_org's GLM-5.2 model in a benchmark, achieving near-top speed without high costs.
@Modular: Portability across CPUs, GPUs, and accelerators sounds simple until you've tried to build it. At #ModCon2026, @clattner…
Modular CEO Chris Lattner and Qualcomm CEO Cristiano Amon discussed portability across CPUs, GPUs, and accelerators at ModCon2026, emphasizing their collaboration to improve software for heterogeneous compute following Qualcomm's acquisition of Modular.