llmserving - わかめtube

Fast LLM Serving with vLLM and PagedAttention

Fast LLM Serving with vLLM and PagedAttention

1 year ago - 32:07

Scalable and Efficient LLM Serving With the VLLM Production Stack - Junchen Jiang & Yue Zhu

The Linux Foundation

Scalable and Efficient LLM Serving With the VLLM Production Stack - Junchen Jiang & Yue Zhu

2 weeks ago - 39:36

vLLM: Easy, Fast, and Cheap LLM Serving for Everyone - Woosuk Kwon & Xiaoxuan Liu, UC Berkeley

vLLM: Easy, Fast, and Cheap LLM Serving for Everyone - Woosuk Kwon & Xiaoxuan Liu, UC Berkeley

9 months ago - 23:33

Create your multi-node LLM serving K8s cluster with one click

Create your multi-node LLM serving K8s cluster with one click

4 months ago - 0:31

What Production-Grade LLM Serving Actually Requires (Infrastructure Deep Dive)

What Production-Grade LLM Serving Actually Requires (Infrastructure Deep Dive)

2 months ago - 5:58

How to Efficiently Serve an LLM?

How to Efficiently Serve an LLM?

11 months ago - 12:13

LLM Serving: The 4 Hard Truths No One Tells You

LLM Serving: The 4 Hard Truths No One Tells You

13 days ago - 49:59

vLLM: Easy, Fast, and Cheap LLM Serving for Everyone - Kaichao You, Tsinghua University

vLLM: Easy, Fast, and Cheap LLM Serving for Everyone - Kaichao You, Tsinghua University

2 days ago - 15:05

Simon Mo on vLLM: Easy, Fast, and Cost-Effective LLM Serving for Everyone

AMD Developer Central

Simon Mo on vLLM: Easy, Fast, and Cost-Effective LLM Serving for Everyone

2 weeks ago - 18:08

[MLArchSys 2025]| Runtime Attestation for Secure LLM Serving in Cloud-Native TEE

[MLArchSys 2025]| Runtime Attestation for Secure LLM Serving in Cloud-Native TEE

1 month ago - 8:26

MobiSys 25 Teaser - EdgeLoRA: An Efficient Multi-Tenant LLM Serving System on Edge Devices

MobiSys 25 Teaser - EdgeLoRA: An Efficient Multi-Tenant LLM Serving System on Edge Devices

2 weeks ago - 1:31

LLM Serving (Rust) demo

LLM Serving (Rust) demo

7 months ago - 5:06

Simplify Your Open-Source LLM Serving with Anyscale's Aviary: Ray Serve Automation & Autoscaling

AI Insight News

Simplify Your Open-Source LLM Serving with Anyscale's Aviary: Ray Serve Automation & Autoscaling

2 years ago - 0:53

[MLArchSys 2025]|SafeKV: Safe KV-Cache Sharing in LLM Serving

[MLArchSys 2025]|SafeKV: Safe KV-Cache Sharing in LLM Serving

1 month ago - 11:27

Lightning Talk: Best Practices for LLM Serving with DRA - Chen Wang & Abhishek Malvankar, IBM

CNCF [Cloud Native Computing Foundation]

Lightning Talk: Best Practices for LLM Serving with DRA - Chen Wang & Abhishek Malvankar, IBM

1 year ago - 9:37

Enabling Cost-Efficient LLM Serving with Ray Serve

Enabling Cost-Efficient LLM Serving with Ray Serve

1 year ago - 30:28

SGLang: An Efficient Open-Source Framework for Large-Scale LLM Serving - Liangsheng Yin

SGLang: An Efficient Open-Source Framework for Large-Scale LLM Serving - Liangsheng Yin

2 days ago - 19:37

E15 | MuxServe: Flexible Multiplexing for Efficient Multiple LLM Serving (ICML'24) 【中文】

MLSys Singapore

E15 | MuxServe: Flexible Multiplexing for Efficient Multiple LLM Serving (ICML'24) 【中文】

1 year ago - 35:14

Ray Aviary: Open-Source Multi-LLM Serving

Ray Aviary: Open-Source Multi-LLM Serving

1 year ago - 19:16

MLSys'25 - LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention

MLSys'25 - LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention

1 month ago - 11:36

Reducing Prefill Delay for LLM Serving in RAG By Sharing Knowledge

Reducing Prefill Delay for LLM Serving in RAG By Sharing Knowledge

1 year ago - 19:10

Offline Energy-Optimal LLM Serving: Workload-Based Energy Models for LLM Inf. on Heterogen. Syst.

Offline Energy-Optimal LLM Serving: Workload-Based Energy Models for LLM Inf. on Heterogen. Syst.

1 year ago - 10:47

Introducing Lemonade Server: Local LLM Serving with GPU and NPU Acceleration

AMD Developer Central

Introducing Lemonade Server: Local LLM Serving with GPU and NPU Acceleration

2 days ago - 6:55

vLLM vs NanoVLLM ⚡ Fast LLM Inference Battle! Which AI Engine Wins?

Serverwala Cloud Data Centers Pvt Ltd

vLLM vs NanoVLLM ⚡ Fast LLM Inference Battle! Which AI Engine Wins?

2 weeks ago - 1:00

MLSys'25 - QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving

MLSys'25 - QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving

1 month ago - 13:45

Efficient LLM Serving on Hybrid Real-time and Best-effort Requests

The Prompt Index

Efficient LLM Serving on Hybrid Real-time and Best-effort Requests

2 months ago - 3:02

What is vLLM? Efficient AI Inference for Large Language Models

What is vLLM? Efficient AI Inference for Large Language Models

1 month ago - 4:58

Legion Retreat 2024 - Low-Latency, High-Performance LLM Serving and Fine-tuning - Zhihao Jia

Legion Programming System

Legion Retreat 2024 - Low-Latency, High-Performance LLM Serving and Fine-tuning - Zhihao Jia

6 months ago - 30:35

Introducing Ray Aviary | 🦜🔍 Open Source Multi-LLM Serving

Introducing Ray Aviary | 🦜🔍 Open Source Multi-LLM Serving

2 years ago - 13:33

TPI-LLM: Serving 70B-scale LLMs Efficiently on Low-resource Edge Devices

TPI-LLM: Serving 70B-scale LLMs Efficiently on Low-resource Edge Devices

9 months ago - 8:46

Mélange - Cost Efficient LLM Serving by Using Mixture of GPUs - Hands on Demo

Mélange - Cost Efficient LLM Serving by Using Mixture of GPUs - Hands on Demo

1 year ago - 10:58

Unlock LLM Speed: VLLM Crushes the Competition!

Unlock LLM Speed: VLLM Crushes the Competition!

1 month ago - 0:48

E07 | Fast LLM Serving with vLLM and PagedAttention

MLSys Singapore

E07 | Fast LLM Serving with vLLM and PagedAttention

1 year ago - 55:36

GOSIM CHINA 2024-Kaichao You vLLM: Easy, Fast, and Cheap LLM Serving for Everyone

GOSIM Foundation

GOSIM CHINA 2024-Kaichao You vLLM: Easy, Fast, and Cheap LLM Serving for Everyone

8 months ago - 31:42

vLLM Inference Engine [ಕನ್ನಡದಲ್ಲಿ] | Easy, Fast, and Cheap LLM Serving with PagedAttention

vLLM Inference Engine [ಕನ್ನಡದಲ್ಲಿ] | Easy, Fast, and Cheap LLM Serving with PagedAttention

1 year ago - 15:45

OSDI '24 - dLoRA: Dynamically Orchestrating Requests and Adapters for LoRA LLM Serving

OSDI '24 - dLoRA: Dynamically Orchestrating Requests and Adapters for LoRA LLM Serving

10 months ago - 14:34

GOSIM CHINA 2024 - Kaichao You: vLLM - Easy, Fast, and Cheap LLM Serving for Everyone

GOSIM Foundation

GOSIM CHINA 2024 - Kaichao You: vLLM - Easy, Fast, and Cheap LLM Serving for Everyone

7 months ago - 30:12

vLLM: Fast & Affordable LLM Serving with PagedAttention | UC Berkeley's Open-Source Library

AI Insight News

vLLM: Fast & Affordable LLM Serving with PagedAttention | UC Berkeley's Open-Source Library

2 years ago - 2:25

Building a Multi-Cluster Privately Hosted LLM Serving Platform on Ku... Julian Bright & Noah Yoshida

CNCF [Cloud Native Computing Foundation]

Building a Multi-Cluster Privately Hosted LLM Serving Platform on Ku... Julian Bright & Noah Yoshida

1 year ago - 25:48

LitServe - LLM Serving Inference Engine - Install and Test Locally

LitServe - LLM Serving Inference Engine - Install and Test Locally

10 months ago - 10:29

InstCache - A Predictive Cache for LLM Serving

InstCache - A Predictive Cache for LLM Serving

5 months ago - 7:08

[vLLM Office Hours #27] Intro to llm-d for Distributed LLM Inference

[vLLM Office Hours #27] Intro to llm-d for Distributed LLM Inference

1 month ago - 1:19:57

LLM inference optimization: Architecture, KV cache and Flash attention

LLM inference optimization: Architecture, KV cache and Flash attention

10 months ago - 44:06

【GOSIM AI Paris 2025】Erwan Gallen & Eldar Kurtic: vLLM: Multi-Accelerator & Quantized LLM Serving

GOSIM Foundation

【GOSIM AI Paris 2025】Erwan Gallen & Eldar Kurtic: vLLM: Multi-Accelerator & Quantized LLM Serving

4 weeks ago - 21:08

R&B song about AnyScale's Aviary, LLM serving library (AI music video) - Sway Ducky

R&B song about AnyScale's Aviary, LLM serving library (AI music video) - Sway Ducky

1 year ago - 0:55

Large Language Model Serving - ML Systems Design Interview

Large Language Model Serving - ML Systems Design Interview

3 months ago - 12:59

vLLM: Easy, Fast, and Cheap LLM Serving, Woosuk Kwon, UC Berkeley

AMD Developer Central

vLLM: Easy, Fast, and Cheap LLM Serving, Woosuk Kwon, UC Berkeley

6 months ago - 22:30

Mastering LLM Inference Optimization From Theory to Cost Effective Deployment: Mark Moyou

Mastering LLM Inference Optimization From Theory to Cost Effective Deployment: Mark Moyou

6 months ago - 33:39

Isaac Chung - Speed up open source LLM-serving with llama-cpp-python

PyCon Lithuania

Isaac Chung - Speed up open source LLM-serving with llama-cpp-python

1 year ago - 23:41

MLSys Singapore

MLSys Singapore

MLSys Seminar @SG is a special interest group for Machine Learning System researchers and engineers in Singapore. We meet ...

@MLSysSingapore subscribers

Autellix: An Efficient Serving Engine for LLM Agents as General Programs

Autellix: An Efficient Serving Engine for LLM Agents as General Programs

4 months ago - 36:28

Serve a Custom LLM for Over 100 Customers

Trelis Research

Serve a Custom LLM for Over 100 Customers

1 year ago - 51:56

Artifical Intelligence (AI) and Machine Learning (ML) for Everyone!

John Savill's Technical Training

Artifical Intelligence (AI) and Machine Learning (ML) for Everyone!

8 hours ago - 27:41

Andes: Defining and Enhancing Quality-of-Experience in LLM-Based Text Streaming Services

Andes: Defining and Enhancing Quality-of-Experience in LLM-Based Text Streaming Services

4 months ago - 46:59

BROS: Revolutionizing LLM Request Handling!

The Prompt Index

BROS: Revolutionizing LLM Request Handling!

2 months ago - 0:43

NDSS 2025 - I Know What You Asked: Prompt Leakage via KV-Cache Sharing in Multi-Tenant LLM Serving

NDSS 2025 - I Know What You Asked: Prompt Leakage via KV-Cache Sharing in Multi-Tenant LLM Serving

2 months ago - 16:22

LMCache Team

LMCache Team

@LMCacheTeam subscribers

Task Scheduling for Decentralized LLM Serving | Dr. Sanjaya Kumar Panda | GenLang 5.0

Task Scheduling for Decentralized LLM Serving | Dr. Sanjaya Kumar Panda | GenLang 5.0

Streamed 8 days ago - 4:06:11

[short] Infinite-LLM: Efficient LLM Service for Long Context with Attention and Distributed KVCache

[short] Infinite-LLM: Efficient LLM Service for Long Context with Attention and Distributed KVCache

1 year ago - 2:59

ACMMobiSys

ACMMobiSys

@ACMMobiSys subscribers

How LLM Use Large Context Windows

How LLM Use Large Context Windows

1 year ago - 3:33

Scaling LLM Inference Globally: Novita AI & Vultr in Partnership

Scaling LLM Inference Globally: Novita AI & Vultr in Partnership

2 weeks ago - 13:44

MIT HAN Lab

MIT HAN Lab

MIT HAN Lab: Hardware, AI and Neural-nets Accelerate Deep Learning Computing Group website: hanlab.mit.edu TinyML ...

@MITHANLab subscribers

kexin.chu2017

kexin.chu2017

@kexin.chu2017 subscribers

[QA] Autellix: An Efficient Serving Engine for LLM Agents as General Programs

[QA] Autellix: An Efficient Serving Engine for LLM Agents as General Programs

4 months ago - 8:20

もっと読み込む