llm-compressor
llm-compressor is LLM-Compressor v0.14.0 Key Highlights ✨ GPTQ Performance Improvements #3128 GPTQ now ships a Triton-based quantization kernel, approximately 15× faster end-to-end than the previous implementatio.... It is ranked #739 on the Dev Radar, in AI dev tools, first seen 1 h ago and shared in 1 post (84 views).
Release v0.14.0 · vllm-project/llm-compressor · GitHub Skip to content Navigation Menu Sign in Appearance settings Search / Sign in Sign up Appearance settings You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} vllm-project / llm-compressor Public Notifications You must be signed in to change notification settings Fork 672 Star 3.8k v0.14.0 Latest Latest Compare Choose a tag to compare Sorry, something went wrong. Filter Loading Sorry,…
What people said about llm-compressor on X
LLM Compressor v0.14.0 is out, and GPTQ just got its biggest speedup since launch. A new Triton kernel makes quantization ~15x faster end to end. Batching layers that share a shape pushes that to ~30x on some MoE workloads. Even the old eager path is 1.5-2x faster. Also new: expanded MSE/iMatrix observers that beat…
— @RedHat_AI, 1 h ago · 4 likes · see the post
Alternatives to llm-compressor
- zcode — builds ZCode, the agent harness for its GLM models. Community researchers found a Repo Wiki feature that generated…
- muse.ai — New connectors are live today. Come build with us.
- academy.dair.ai — Chat with Paper
- hermes-agent.nousresearch.com — some integrations feel very hacker-y, require a lot of DIY setup
- classifier.dev — now outperforms jev and is free
- StepFun Open Platform — Step API · Stable · High-Performance · Easy Integration. Leading models and tools to accelerate the deployment of your…
llm-compressor in numbers
- Rank on the Dev Radar: #739 of 2631
- Shared in 1 post by 1 account: @RedHat_AI
- 84 views on those posts
- First seen 1 h ago, last shared 1 h ago
- Pricing seen by Jev: open source
- Market: AI dev tools
FAQ
What is llm-compressor?
LLM-Compressor v0.14.0 Key Highlights ✨ GPTQ Performance Improvements #3128 GPTQ now ships a Triton-based quantization kernel, approximately 15× faster end-to-end than the previous implementatio... It was first shared on X 1 h ago and is ranked #739 on the Dev Radar.
Is llm-compressor free?
It is open source.
Who shared llm-compressor?
1 account on X, including @RedHat_AI, in 1 post totalling 84 views.
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 22.7k posts from 5k X accounts over the last 21 days, 2.6k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-23 17:13 UTC. Full method.