| | Anyscale Endpoints: LLM inference and fine-tuning (anyscale.com) |
| 1 point by robertnishihara on Oct 25, 2023 | past |
|
| | Anyscale Private Endpoints and Anyscale Endpoints Fine-Tuning (anyscale.com) |
| 3 points by robertnishihara on Oct 24, 2023 | past |
|
| | Loading LLM (Llama-2 70B) 20x faster with Anyscale Endpoints (anyscale.com) |
| 5 points by oldcap on Oct 13, 2023 | past | 2 comments |
|
| | Loading Llama-2 70B 20x faster with Anyscale Endpoints (anyscale.com) |
| 1 point by fgfm on Oct 12, 2023 | past | 1 comment |
|
| | Loading Llama-2 70B 20x faster with Anyscale Endpoints (anyscale.com) |
| 4 points by robertnishihara on Oct 12, 2023 | past |
|
| | Loading Llama-2 70B 20x faster with Anyscale Endpoints (anyscale.com) |
| 3 points by george_123 on Oct 11, 2023 | past |
|
| | Scaling data loading for ML training with Ray Data (anyscale.com) |
| 4 points by swang93 on Sept 15, 2023 | past | 1 comment |
|
| | Cloud Infrastructure for LLM and Generative AI Applications (anyscale.com) |
| 4 points by ameerh on Sept 14, 2023 | past |
|
| | Production Guide for Building Rag-Based LLM Applications (anyscale.com) |
| 11 points by GokuMohandas on Sept 13, 2023 | past |
|
| | Fine-Tuning LLMs: LoRA or Full-Parameter? An In-Depth Analysis with Llama 2 (anyscale.com) |
| 22 points by ameerh on Sept 6, 2023 | past | 2 comments |
|
| | ByteDance Scales Offline Inference with Multi-Modal LLMs to 200 TB Data (anyscale.com) |
| 1 point by jamesblonde on Sept 4, 2023 | past |
|
| | ThirdAI Uses Ray for Parallel Training of Billion-Parameter NN on Commodity CPUs (anyscale.com) |
| 78 points by thirdailab on Aug 30, 2023 | past | 15 comments |
|
| | Llama 2 is about as factually accurate as GPT-4 for summaries and is 30X cheaper (anyscale.com) |
| 143 points by pallas_athena on Aug 29, 2023 | past | 54 comments |
|
| | Fine Tuning is for form not facts (anyscale.com) |
| 2 points by amrrs on Aug 27, 2023 | past |
|
| | Llama 2 is about as factually accurate as GPT-4 for summaries and is 30X cheaper (anyscale.com) |
| 19 points by robertnishihara on Aug 23, 2023 | past |
|
| | ByteDance Scales Offline Inference with Multi-Modal LLMs to 200 TB Data (anyscale.com) |
| 7 points by robertnishihara on Aug 15, 2023 | past |
|
| | Continuous batching to increase LLM inference throughput and reduce p50 latency (anyscale.com) |
| 110 points by michellezzz on Aug 15, 2023 | past | 20 comments |
|
| | [flagged] Numbers every LLM Developer should know (anyscale.com) |
| 95 points by davidwu on Aug 12, 2023 | past | 18 comments |
|
| | Fine-Tuning Llama-2: A Comprehensive Case Study for Tailoring Custom Models (anyscale.com) |
| 308 points by robertnishihara on Aug 11, 2023 | past | 59 comments |
|
| | Continuous batching enables 23x throughput in LLM inference (anyscale.com) |
| 2 points by richardliaw on June 23, 2023 | past |
|
| | Aviary: Compare Open Source LLMs for cost, latency and quality (anyscale.com) |
| 6 points by robnsngh on June 1, 2023 | past |
|
| | Anyscale's Aviary is a dashboard for evaluating Open Source LLMs (anyscale.com) |
| 14 points by richardliaw on May 31, 2023 | past | 3 comments |
|
| | Anyscale's Aviary: Open-Source Multi-LLM Serving (anyscale.com) |
| 24 points by Thicken2320 on May 31, 2023 | past | 1 comment |
|
| | How to build a LLM search engine using a self-hosted LLM (anyscale.com) |
| 3 points by richardliaw on April 21, 2023 | past |
|
| | Ray solves common production challenges for generative AI infrastructure (anyscale.com) |
| 1 point by tim_sw on March 28, 2023 | past |
|
| | Ray breaks the $1/TB barrier as the world’s most cost-efficient sorting system (anyscale.com) |
| 36 points by mahvas on Jan 24, 2023 | past | 8 comments |
|
| | Training One Million Machine Learning Models in Record Time with Ray (anyscale.com) |
| 1 point by robertnishihara on Dec 18, 2022 | past |
|
| | Serving PyTorch Models with FastAPI and Ray Serve (anyscale.com) |
| 2 points by walterbell on Dec 17, 2022 | past |
|
| | Ant Group – scaling to 1.37M QPS on Ray (anyscale.com) |
| 3 points by george_123 on Dec 13, 2022 | past | 1 comment |
|
| | Cross-language, distributed model inference framework: Serve with Java API (anyscale.com) |
| 1 point by jsd_dmatrix on Dec 13, 2022 | past | 1 comment |
|
|
| More |
