Benchmarks on NVIDIA’s Transformer Engine, which boosts FP8 performance by an impressive 60% on GPT3-style model testing on NVIDIA H100 Tensor Core GPUs.
Lambda will be one of the first cloud providers in the world to offer customers access to NVIDIA H200 Tensor Core GPUs through Lambda Cloud Clusters.
Lambda Cloud Clusters are now available with the NVIDIA GH200 Grace Hopper Superchip. A single GH200 has 576GB of coherent memory for unmatched efficiency.
GPU benchmarks on Lambda’s offering of the NVIDIA H100 SXM5 vs the NVIDIA A100 SXM4 using DeepChat’s 3-step training example.
Persistent storage for Lambda Cloud is expanding. Filesystems are now available for all regions except Utah, which is coming very soon.
This analysis explores whether a Large Language Model, such as OpenAI's GPT, can assist in helping human readers digest scientific reviews.
Lambda has launched a new Hyperplane server combining the fastest GPU on the market, NVIDIA H100, with the world’s best data center CPU, AMD EPYC 9004.
How to use FlashAttention-2 on Lambda Cloud, including H100 vs A100 benchmark results for training GPT-3-style models using the new model.
On-demand HGX H100 systems with 8x NVIDIA H100 SXM instances are now available on Lambda Cloud for only $2.59/hr/GPU.
Unlock the potential of open-source LLMs by hosting your very own langchain+Falcon+Chroma application. Upload a PDF and engage in Q&A about its contents.
This blog post provides instructions on how to fine tune LLaMA 2 models on Lambda Cloud using a $0.60/hr A10 GPU.
How to build the GPU infrastructure needed to pretrain LLM and Generative AI models from scratch (e.g. GPT-4, LaMDA, LLaMA, BLOOM).
Learn how to fine-tune Falcon LLM 7B/40B on a single GPU with LoRA and quantization, enabling data parallelism for linear scaling across multiple GPUs.
...