aireilly

LLM Compressor v0.8.0 release notes

This LLM Compressor v0.8.0 release introduces the following new features and enhancements:

• Support for multiple modifiers in oneshot compression runs
• Quantization and calibration support for Qwen3 models including FP8 quantization support for Qwen3 VL MoE models
• Transforms support for non-full-size rotation sizes
• Improved accuracy recovery by updating W4A16 schemes to use actorder "weight" by default

Support for multiple modifiers in oneshot compression runs ✨

aireilly

LLM Compressor v0.7.0 release notes

This LLM Compressor v0.7.0 release introduces major new features and enhancements:

• Apply multiple compressors to a single model for mixed-precision quantization
• Support for DeepSeekV3-style block FP8 quantization
• Configurable Observer arguments in config.yaml
• Expanded Mixture of Experts (MoE) calibration support, including NVFP4
• Llama4 quantization support with vLLM compatibility
• Simplified and unified Recipe classes for easier usage and debugging

aireilly

LMM Compressor docs proposal

• About large language model optimization
  • Supported model types for optimization
• Deciding on a compression strategy
  • Supported compression algorithms and formats
  • Advanced compression techniques and features
• Evaluating model quality

aireilly

Configuring VS Code and MCP to vibe with JIRA, GitHub, and local file systems

This gist describes how to configure VS Code to use Red Hat approved language models with the following MCP (Model Context Protocol) servers:

• GitHub

• JIRA

• Local files

• Web search

Configuring VS Code to use a Red Hat approved language model

aireilly

Locate the section for your github remote in the .git/config file. It looks like this:

[remote "origin"]
	fetch = +refs/heads/*:refs/remotes/origin/*
	url = git@github.com:joyent/node.git

Now add the line fetch = +refs/pull/*/head:refs/remotes/origin/pr/* to this section. Obviously, change the github url to match your project's URL. It ends up looking like this: