Home / Companies / Anyscale / Hacker News

Anyscale on HN

57 posts with 1+ points since 2022

Filters
Since:
Posts by Month (57 total)
Hacker News Posts
Title Points Comments Date
Fine-Tuning Llama-2: A Comprehensive Case Study for Tailoring Custom Models 308 59 2023-08-11
Continuous batching to increase LLM inference throughput and reduce p50 latency 110 20 2023-08-15
Numbers every LLM Developer should know 95 18 2023-08-12
ThirdAI Uses Ray for Parallel Training of Billion-Parameter NN on Commodity CPUs 78 15 2023-08-30
Uv and Ray: Pain-Free Python Dependencies in Clusters 44 10 2025-06-27
Ray breaks the $1/TB barrier as the world’s most cost-efficient sorting system 36 8 2023-01-24
Anyscale's Aviary: Open-Source Multi-LLM Serving 24 1 2023-05-31
Fine-Tuning LLMs: LoRA or Full-Parameter? An In-Depth Analysis with Llama 2 22 2 2023-09-06
Llama 2 is about as factually accurate as GPT-4 for summaries and … 19 0 2023-08-23
ByteDance Scales Offline Inference with Multi-Modal LLMs to 200 TB Data 7 0 2023-08-15
Aviary: Compare Open Source LLMs for cost, latency and quality 6 0 2023-06-01
Lessons from training a Stable Diffusion model on 2B images 5 0 2024-05-11
Scaling data loading for ML training with Ray Data 4 1 2023-09-15
Cloud Infrastructure for LLM and Generative AI Applications 4 0 2023-09-14
Model Batch Inference in Ray: Actors, ActorPool, and Datasets 4 0 2022-11-04
67% Cost Savings with PD Disaggregation Using Ray and vLLM on AMD … 4 0 2026-06-16
Loading Llama-2 70B 20x faster with Anyscale Endpoints 3 0 2023-10-11
Ant Group – scaling to 1.37M QPS on Ray 3 1 2022-12-13
Ant Group Uses Ray to Build a Large-Scale Online Serverless Platform 3 1 2022-12-12
Anyscale Private Endpoints and Anyscale Endpoints Fine-Tuning 3 0 2023-10-24
How to build a LLM search engine using a self-hosted LLM 3 0 2023-04-21
An informal introduction to reinforcement learning 3 0 2022-02-23
An OSS Stack for AI Compute: Kubernetes + Ray + PyTorch + … 3 0 2025-06-15
Joins and Hash-Shuffle in Ray Data 3 0 2025-07-09
High Performance Distributed Inference with Ray Serve LLM 3 0 2026-06-18
Anyscale signs definitive agreement to join Nscale 3 0 2026-07-30
Building RAG-Based LLM Applications for Production 2 0 2024-02-14
Anyscale Appoints Keerti Melkote as CEO 2 0 2024-07-31
Canva Built a Modern AI Platform Using Anyscale 2 0 2024-04-03
Comparing LLM Performance: Introducing the Open Source Leaderboard for LLM APIs 2 0 2023-12-21
Anyscale Endpoints: JSON Mode and Function Calling Features 2 0 2023-12-14
Reproducible Performance Metrics for LLM Inference 2 0 2023-11-02
Fine Tuning is for form not facts 2 0 2023-08-27
Serving PyTorch Models with FastAPI and Ray Serve 2 None 2022-12-17
Ray Datasets for large-scale machine learning ingest and scoring 2 None 2022-02-25
Ray 1.10 Released 2 None 2022-02-25
Large-Scale Deployment of Ray in Tencent's Weixin AI Infrastructure 2 0 2025-07-01
Native LLM APIs in Ray Data and Ray Serve 2 0 2025-07-10
Massively Parallel Agentic Simulations with Ray 2 0 2025-09-11
Major upgrades to Ray Serve: 88% lower latency and 11.1x higher throughput 2 1 2026-03-26
Data Processing Is Becoming a GPU Workload 2 0 2026-06-16
Direct Preference Optimization with Synthetic Data on Anyscale 1 None 2024-08-21
Building an LLM Router for High-Quality and Cost-Effective Responses 1 None 2024-07-02
End-to-End LLM Workflows Guide 1 None 2024-06-18
Fine-tuning LLMs for longer context and better RAG systems 1 None 2024-02-13
RAG at Scale: 10x Cheaper Embedding Computations with Anyscale and Pinecone 1 None 2024-01-16
LLM summarization: A case study of human, Llama-2, & GPT-4 summarization quality 1 None 2023-11-10
Anyscale Endpoints: LLM inference and fine-tuning 1 None 2023-10-25
Ray solves common production challenges for generative AI infrastructure 1 None 2023-03-28
Training One Million Machine Learning Models in Record Time with Ray 1 None 2022-12-18
Gang Scheduling Ray Clusters on K8s with Multi-Cluster-App-Dispatcher (MCAD) 1 None 2022-11-16
Redis in Ray: Past and Future 1 None 2022-03-18
Ray 1.11 Released 1 None 2022-03-11
Open Source RL Libraries for LLMs 1 None 2025-07-02
Deploy DeepSeek‑R1 with VLLM and Ray Serve on Kubernetes 1 None 2025-08-11
LLM Inference with Ray: Expert parallelism and prefill/decode disaggregation 1 None 2025-11-28
LLM Engine Orchestration for Performance 1 None 2025-10-07
Plushcap, by Matt Makai. 2021-2026.