Search: andscape.com | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

1.

The Gentrification of College Hoops

3 years ago

2 points

2.

The gut-wrenching history of black babies and alligators

4 years ago

2 points

3.

Design considerations for RAG application in production mode

3 years ago

3 points

4.

Fine-Tuning Llama-2: A Comprehensive Case Study for Tailoring Custom Models

3 years ago

robertnishihara

308 points

5.

Llama 2 is about as factually accurate as GPT-4 for summaries and is 30X cheaper

3 years ago

143 points

6.

Continuous batching to increase LLM inference throughput and reduce p50 latency

3 years ago

110 points

7.

Numbers every LLM Developer should know

3 years ago

95 points

8.

ThirdAI Uses Ray for Parallel Training of Billion-Parameter NN on Commodity CPUs

3 years ago

78 points

9.

Uv and Ray: Pain-Free Python Dependencies in Clusters

a year ago

robertnishihara

44 points

10.

Ray breaks the $1/TB barrier as the world’s most cost-efficient sorting system

3 years ago

36 points

11.

Anyscale's Aviary: Open-Source Multi-LLM Serving

3 years ago

24 points

12.

Fine-Tuning LLMs: LoRA or Full-Parameter? An In-Depth Analysis with Llama 2

3 years ago

22 points

13.

LightGBM vs. XGBoost: Which distributed version is faster?

5 years ago

22 points

14.

Llama 2 is about as factually accurate as GPT-4 for summaries and is 30X cheaper

3 years ago

robertnishihara

19 points

15.

Anyscale's Aviary is a dashboard for evaluating Open Source LLMs

aviary.anyscale.com

3 years ago

14 points

16.

Production Guide for Building Rag-Based LLM Applications

3 years ago

11 points

17.

Multi-node distributed training for PyTorch Lightning made easy

5 years ago

9 points

18.

ByteDance Scales Offline Inference with Multi-Modal LLMs to 200 TB Data

3 years ago

robertnishihara

7 points

19.

Aviary: Compare Open Source LLMs for cost, latency and quality

aviary.anyscale.com

3 years ago

6 points

20.

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

3 years ago

5 points

21.

Lessons from training a Stable Diffusion model on 2B images

2 years ago

robertnishihara

5 points

22.

Scaling data loading for ML training with Ray Data

3 years ago

4 points

23.

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

8 days ago

robertnishihara

4 points

24.

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

3 years ago

robertnishihara

4 points

25.

Cloud Infrastructure for LLM and Generative AI Applications

3 years ago

4 points

26.

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

4 years ago

4 points

27.

Ben Lorica blog post on enterprise applications of reinforcement learning

6 years ago

4 points

28.

Ant Group – scaling to 1.37M QPS on Ray

4 years ago

3 points

29.

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

4 years ago

3 points

30.

High Performance Distributed Inference with Ray Serve LLM

5 days ago

robertnishihara

3 points