https://sachinkalsi.github.io/blog/key-takeaways-from-building-multiple-machine-learning-models/ 2022-03-19T00:00:00+05:30 https://sachinkalsi.github.io/blog/flashattention-understanding-gpu-architecture-part-1/ 2023-10-23T00:00:00+05:30 https://sachinkalsi.github.io/blog/a-deep-dive-into-flashattention-v1-part-3/ 2023-10-24T00:00:00+05:30 https://sachinkalsi.github.io/blog/flashattention-an-advancement-in-gpu-acceleration-for-training-llms/ 2023-10-24T00:00:00+05:30 https://sachinkalsi.github.io/blog/why-does-my-text-look-weird/ 2025-12-22T00:00:00+05:30 https://sachinkalsi.github.io/blog/why-do-we-use-negative-inf-for-masking/ 2025-12-23T00:00:00+05:30 https://sachinkalsi.github.io/blog/gemma-3-explained-how-google-built-a-faster-leaner-multimodal-ai/ 2026-02-01T00:00:00+05:30 https://sachinkalsi.github.io/blog/constrained-decoding-forcing-llms-to-respect-your-taxonomy/ 2026-05-05T00:00:00+05:30 https://sachinkalsi.github.io/blog/what-i-learned-from-finewebs-15t-token-recipe/ 2026-06-28T00:00:00+05:30 https://sachinkalsi.github.io/blog/ https://sachinkalsi.github.io/ https://sachinkalsi.github.io/google1af9172c4c1c534f.html 2026-09-07T23:54:20+05:30 https://sachinkalsi.github.io/resume/sachin_kalsi.pdf 2026-09-07T23:54:20+05:30