cr7258/ai-infra-learning

This repository organizes materials, recordings, and schedules related to AI-infra learning meetings.

596

57 commits

updated Mar 1, 2026

README

AI Infra 学习会议

主题	时间	预习资料	录频	文档	问题反馈 & 课后思考题
vLLM Quickstart	2025-05-11	Doc: vLLM	AI INFRA 学习 01 - LLM 全景图介绍/vLLM 快速入门	01-vllm-quickstart
PagedAttention	2025-05-25	Blog: vLLM: Easy, Fast, and Cheap LLM Serving with PagedAttention Paper: Efficient Memory Management for Large Language Model Serving with PagedAttention Video: Fast LLM Serving with vLLM and PagedAttention	AI INFRA 学习 02 - vLLM PagedAttention 论文精读	02-pagedattention	02-PagedAttention 问题反馈
Prefix Caching	2025-06-08	Doc: Automatic Prefix Caching Design Doc: Automatic Prefix Caching Paper: SGLang: Efficient Execution of Structured Language Model Programs	AI INFRA 学习 03 - Prefix Caching 原理详解	03-prefix-caching
Speculative Decoding	2025-06-22	Doc: Speculative Decoding Blog: How Speculative Decoding Boosts vLLM Performance by up to 2.8x Video: Hacker's Guide to Speculative Decoding in VLLM Video: Speculative Decoding in vLLM Paper: Accelerating Large Language Model Decoding with Speculative Sampling Paper: Fast Inference from Transformers via Speculative Decoding	AI INFRA 学习 04 - Speculative Decoding 实现方案	04-speculative-decoding
Chunked-Prefills	2025-07-13	Doc: vLLM Chunked Prefill Paper: SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills Paper: DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference Paper: Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve	AI INFRA 学习 05 - Chunked-Prefills 分块预填充	05-chunked-prefills	05-Chunked-Prefills 问题反馈 & 课后思考题
Disaggregating Prefill and Decoding	2025-09-21	Doc: Disaggregated Prefilling Doc: vLLM Production Stack Disaggregated Prefill Paper: DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving Paper: Splitwise: Efficient generative LLM inference using phase splitting Video: vLLM Office Hours - Disaggregated Prefill and KV Cache Storage in vLLM	AI INFRA 学习 06 - PD 分离推理架构详解	06-disaggregating-prefill-and-decoding	06-PD 分离问题反馈
Inference Platform	2026-03-01	llm-d NVIDIA Dynamo AIBrix Kthena RoleBasedGroup	AI INFRA 学习 07 - 推理平台全景	07-inference-platform
LoRA Adapters		Doc: LoRA Adapters Paper: LoRA: Low-Rank Adaptation of Large Language Models
Quantization

交流群（加群请备注来意）

微信公众号

搜索框传播样式-白色版

Contributors

cr7258

57 commits

Similar repos

patchy631/time-to-first-token

A 10-week, 30-minutes-a-day roadmap for LLM inference serving and optimization. vLLM, SGLang,…

957

Zhengyang-Gou/AI_Infrastructure

luhengshiwo/LLMForEverybody

每个人都能看懂的大模型知识分享，LLMs春/秋招大模型面试前必看，让你和面试官侃侃而谈

7,378

gpu-mode/awesomeMLSys

An ML Systems Onboarding list

1,131

CarrotShoo/vllm-old

A high-throughput and memory-efficient inference and serving engine for LLMs

shishishu/LLM-Inference-Acceleration

LLM Inference with Deep Learning Accelerator.

galeselee/Awesome_LLM_System-PaperList

Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become…

284

xingyaoww/vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

cr7258/ai-infra-learning

This repository organizes materials, recordings, and schedules related to AI-infra learning meetings.

596

57 commits

updated Mar 1, 2026

See the code

README

AI Infra 学习会议

主题	时间	预习资料	录频	文档	问题反馈 & 课后思考题
vLLM Quickstart	2025-05-11	Doc: vLLM	AI INFRA 学习 01 - LLM 全景图介绍/vLLM 快速入门	01-vllm-quickstart
PagedAttention	2025-05-25	Blog: vLLM: Easy, Fast, and Cheap LLM Serving with PagedAttention Paper: Efficient Memory Management for Large Language Model Serving with PagedAttention Video: Fast LLM Serving with vLLM and PagedAttention	AI INFRA 学习 02 - vLLM PagedAttention 论文精读	02-pagedattention	02-PagedAttention 问题反馈
Prefix Caching	2025-06-08	Doc: Automatic Prefix Caching Design Doc: Automatic Prefix Caching Paper: SGLang: Efficient Execution of Structured Language Model Programs	AI INFRA 学习 03 - Prefix Caching 原理详解	03-prefix-caching
Speculative Decoding	2025-06-22	Doc: Speculative Decoding Blog: How Speculative Decoding Boosts vLLM Performance by up to 2.8x Video: Hacker's Guide to Speculative Decoding in VLLM Video: Speculative Decoding in vLLM Paper: Accelerating Large Language Model Decoding with Speculative Sampling Paper: Fast Inference from Transformers via Speculative Decoding	AI INFRA 学习 04 - Speculative Decoding 实现方案	04-speculative-decoding
Chunked-Prefills	2025-07-13	Doc: vLLM Chunked Prefill Paper: SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills Paper: DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference Paper: Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve	AI INFRA 学习 05 - Chunked-Prefills 分块预填充	05-chunked-prefills	05-Chunked-Prefills 问题反馈 & 课后思考题
Disaggregating Prefill and Decoding	2025-09-21	Doc: Disaggregated Prefilling Doc: vLLM Production Stack Disaggregated Prefill Paper: DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving Paper: Splitwise: Efficient generative LLM inference using phase splitting Video: vLLM Office Hours - Disaggregated Prefill and KV Cache Storage in vLLM	AI INFRA 学习 06 - PD 分离推理架构详解	06-disaggregating-prefill-and-decoding	06-PD 分离问题反馈
Inference Platform	2026-03-01	llm-d NVIDIA Dynamo AIBrix Kthena RoleBasedGroup	AI INFRA 学习 07 - 推理平台全景	07-inference-platform
LoRA Adapters		Doc: LoRA Adapters Paper: LoRA: Low-Rank Adaptation of Large Language Models
Quantization

交流群（加群请备注来意）

微信公众号

搜索框传播样式-白色版

Similar repos

patchy631/time-to-first-token

A 10-week, 30-minutes-a-day roadmap for LLM inference serving and optimization. vLLM, SGLang,…

957

Zhengyang-Gou/AI_Infrastructure

luhengshiwo/LLMForEverybody

每个人都能看懂的大模型知识分享，LLMs春/秋招大模型面试前必看，让你和面试官侃侃而谈

7,378

gpu-mode/awesomeMLSys

An ML Systems Onboarding list

1,131

CarrotShoo/vllm-old

A high-throughput and memory-efficient inference and serving engine for LLMs

shishishu/LLM-Inference-Acceleration

LLM Inference with Deep Learning Accelerator.

galeselee/Awesome_LLM_System-PaperList

Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become…

284

xingyaoww/vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

Contributors

cr7258

57 commits