Hacker News: harshuljain13https://news.ycombinator.com/user?id=harshuljain13Hacker News RSShttps://hnrss.org/hnrss v2.1.1Sat, 13 Jun 2026 02:18:42 +0000<![CDATA[Free LLM inference handbook: 100 engineers cloned it in week 1]]>Article URL: https://github.com/harshuljain13/llm-inference-at-scale

Comments URL: https://news.ycombinator.com/item?id=48424467

Points: 2

# Comments: 0

]]>Sat, 06 Jun 2026 12:37:09 +0000https://github.com/harshuljain13/llm-inference-at-scaleharshuljain13https://news.ycombinator.com/item?id=48424467https://news.ycombinator.com/item?id=48424467<![CDATA[Why LLM decode is memory-bound, not compute-bound]]>Article URL: https://github.com/harshuljain13/llm-inference-at-scale/blob/master/content/00_foundations/00.1_why_llm_inference_is_different/why_llm_inference_is_different.md

Comments URL: https://news.ycombinator.com/item?id=48307631

Points: 5

# Comments: 0

]]>Thu, 28 May 2026 11:53:06 +0000https://github.com/harshuljain13/llm-inference-at-scale/blob/master/content/00_foundations/00.1_why_llm_inference_is_different/why_llm_inference_is_different.mdharshuljain13https://news.ycombinator.com/item?id=48307631https://news.ycombinator.com/item?id=48307631