Multiple model copies on a single EC2 instance

What's Changed

• Fix EC2 container not running due to bad flag by @dheerajoruganty in #185
• remove unecessary --runtime=nvidia from the docker command by @madhurprash in #186
• Multi model w djl by @aarora79 in #191

Full Changelog: v2.0.5...v2.0.6

Intel CPU support with vLLM

What's Changed

• add ec2 instructions to enable docker runs without sudo by @madhurprash in #181
• clean up analytics, create documentation for it by @madhurprash in #182
• prompt template key fix by @madhurprash in #184
• Support for Intel Instances and Configuration Updates by @dheerajoruganty in #183

Full Changelog: v2.0.4...v2.0.5

AMD CPU support

What's Changed

• Deployment Support for x86 AMD CPUs on EC2 by @dheerajoruganty in #178
• amd support by @aarora79 in #179

Full Changelog: v2.0.3...v2.0.4

EFA support for /tmp dir, Mistral on AWS Chips

What's Changed

• config file update for llama3-8b by @madhurprash in #175
• Added Inital Support for AMD x86 CPUs by @dheerajoruganty in #177
• Adding support for custom tmp directory + preliminary config files for mistral on inf2/trn1 by @madhurprash in #176

Full Changelog: v2.0.2...v2.0.3

Llama3.1-8b on SageMaker, DJL serving fixes

What's Changed

• Update CITATION.cff by @aarora79 in #172
• Adding youtube logo on embedded image link by @madhurprash in #173
• Update README.md by @aarora79 in #174

Full Changelog: v2.0.1...v2.0.2

Model evaluations

What's Changed

• Aws inf by @antara678 in #166

Full Changelog: v1.0.52...v2.0.0

Llama3.1 on AWS Chips

What's Changed

• Support for inf2 instance by @antara678 in #158
• Support for llama3.1 on Inf2 + Other neuron deployment updates by @madhurprash in #159
• updating the manifext.txt file by @madhurprash in #160
• updated neuron deploy code by @antara678 in #161
• Update neuron_deploy.py with logger statements by @antara678 in #162
• support for llama3.1 on neuron + use_messages_api metadata addition by @madhurprash in #164
• Add files via upload by @antara678 in #163

Full Changelog: v1.0.51...v1.0.52

FMBench website, Llama3.1

What's Changed

• Update config-ec2-llama3-8b-inf2-48xl.yml by @antara678 in #148
• config file for llama 2 70B by @antara678 in #134
• fmbench website by @antara678 in #151
• Gh website-updated logo path by @antara678 in #152
• adding support for llama3.1 on Amazon Bedrock by @madhurprash in #156

Full Changelog: v1.0.50...v1.0.51

FMBench support for RAG + Model evaluations

This version contains [Work in Progress] code for evaluating both:

1. Majority Vote: Using a Panel of LLM Evaluators to check for RAG eval on whether a given candidate model output is correct or incorrect.
2. Average Pooling: Using a Panel of LLM Evaluators to evaluate candidate model responses using 'user-defined' subjective evaluation criteria.

Llama3-8b on EC2 inf2.48xlarge

What's Changed

• Update README.md by @antara678 in #143
• Ec2 inf2 by @madhurprash in #145
• Update manifest.txt by @antara678 in #146
• Add Material for Mkdocs Config by @dheerajoruganty in #147

Full Changelog: v1.0.49...v1.0.50