Search: appscale.com | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

61.

67% Cost Savings with PD Disaggregation Using Ray and vLLM on AMD MI325X

7 days ago

robertnishihara

4 points

62.

Loading Llama-2 70B 20x faster with Anyscale Endpoints

3 years ago

robertnishihara

4 points

63.

Cloud Infrastructure for LLM and Generative AI Applications

3 years ago

4 points

64.

Model Batch Inference in Ray: Actors, ActorPool, and Datasets

4 years ago

4 points

65.

Ben Lorica blog post on enterprise applications of reinforcement learning

6 years ago

4 points

66.

Ant Group – scaling to 1.37M QPS on Ray

4 years ago

3 points

67.

Ant Group Uses Ray to Build a Large-Scale Online Serverless Platform

4 years ago

3 points

68.

High Performance Distributed Inference with Ray Serve LLM

5 days ago

robertnishihara

3 points

69.

Joins and Hash-Shuffle in Ray Data

a year ago

robertnishihara

3 points

70.

An OSS Stack for AI Compute: Kubernetes + Ray + PyTorch + LLM

a year ago

3 points

71.

Building Rag-Based LLM Applications for Production

3 years ago

robertnishihara

3 points

72.

Anyscale Private Endpoints and Anyscale Endpoints Fine-Tuning

3 years ago

robertnishihara

3 points

73.

Loading Llama-2 70B 20x faster with Anyscale Endpoints

3 years ago

3 points

74.

How to build a LLM search engine using a self-hosted LLM

3 years ago

3 points

75.

An informal introduction to reinforcement learning

4 years ago

robertnishihara

3 points

76.

Why Third Generation ML Platforms Are More Performant

5 years ago

robertnishihara

3 points

77.

The Third Generation of Production ML Architectures

5 years ago

robertnishihara

3 points

78.

6 years ago

robertnishihara

3 points

79.

Enterprise Applications of Reinforcement Learning

6 years ago

robertnishihara

3 points

80.

Major upgrades to Ray Serve: 88% lower latency and 11.1x higher throughput

3 months ago

robertnishihara

2 points

81.

Mobile App Marketing Tool

12 years ago

2 points

82.

Data Processing Is Becoming a GPU Workload

7 days ago

robertnishihara

2 points

83.

Massively Parallel Agentic Simulations with Ray

9 months ago

robertnishihara

2 points

84.

Native LLM APIs in Ray Data and Ray Serve

a year ago

robertnishihara

2 points

85.

Large-Scale Deployment of Ray in Tencent's Weixin AI Infrastructure

a year ago

robertnishihara

2 points

86.

Anyscale Appoints Keerti Melkote as CEO

2 years ago

2 points

87.

Canva Built a Modern AI Platform Using Anyscale

2 years ago

robertnishihara

2 points

88.

Building RAG-Based LLM Applications for Production

2 years ago

robertnishihara

2 points

89.

Comparing LLM Performance: Introducing the Open Source Leaderboard for LLM APIs

3 years ago

robertnishihara

2 points

90.

Anyscale Endpoints: JSON Mode and Function Calling Features

3 years ago

robertnishihara

2 points