{
 "schema_version": 1,
 "generated": "2026-10-20",
 "repo": "amitshekhariitbhu/llm-inference-engineering",
 "name": "llm-inference-engineering",
 "owner": "amitshekhariitbhu",
 "slug": "amitshekhariitbhu-llm-inference-engineering",
 "github": "https://github.com/amitshekhariitbhu/llm-inference-engineering",
 "what": "A free, step-by-step learning series of blog posts and videos on LLM inference engineering, covering topics such as KV cache, PagedAttention, continuous batching, and speculative decoding.",
 "why": "",
 "language": "Markdown",
 "requirements": [
  "A web browser to open the linked blog posts",
  "Basic familiarity with how text generation works, or willingness to start with the Part 1 basics"
 ],
 "audience_note": "Software engineers and ML practitioners who need to understand how LLMs are served and sped up before they build or tune an inference system.",
 "risk": "none",
 "section": "earlier",
 "weekly_rank": null,
 "category": "Research",
 "url": "https://dedupedai.com/use-cases/amitshekhariitbhu-llm-inference-engineering/",
 "use_case_count": 4,
 "use_cases": [
  {
   "id": "amitshekhariitbhu-llm-inference-engineering--learn-how-llm-text-generation-works",
   "title": "Learn how LLMs generate text one token at a time",
   "best": true,
   "url": "https://dedupedai.com/use-cases/amitshekhariitbhu-llm-inference-engineering/learn-how-llm-text-generation-works/",
   "json": "https://dedupedai.com/use-cases/u/amitshekhariitbhu-llm-inference-engineering/learn-how-llm-text-generation-works.json"
  },
  {
   "id": "amitshekhariitbhu-llm-inference-engineering--pick-a-memory-optimization-for-kv-cache",
   "title": "Pick a KV cache memory technique for long prompts",
   "best": false,
   "url": "https://dedupedai.com/use-cases/amitshekhariitbhu-llm-inference-engineering/pick-a-memory-optimization-for-kv-cache/",
   "json": "https://dedupedai.com/use-cases/u/amitshekhariitbhu-llm-inference-engineering/pick-a-memory-optimization-for-kv-cache.json"
  },
  {
   "id": "amitshekhariitbhu-llm-inference-engineering--choose-a-decoding-speedup-technique",
   "title": "Choose a faster decoding method for slow responses",
   "best": false,
   "url": "https://dedupedai.com/use-cases/amitshekhariitbhu-llm-inference-engineering/choose-a-decoding-speedup-technique/",
   "json": "https://dedupedai.com/use-cases/u/amitshekhariitbhu-llm-inference-engineering/choose-a-decoding-speedup-technique.json"
  },
  {
   "id": "amitshekhariitbhu-llm-inference-engineering--understand-serving-many-users-at-once",
   "title": "Understand how LLM servers handle many users at once",
   "best": false,
   "url": "https://dedupedai.com/use-cases/amitshekhariitbhu-llm-inference-engineering/understand-serving-many-users-at-once/",
   "json": "https://dedupedai.com/use-cases/u/amitshekhariitbhu-llm-inference-engineering/understand-serving-many-users-at-once.json"
  }
 ],
 "disclaimer": "Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk."
}