Skip to content

Glq

v0.1.3 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 2mo Model Serving & MLOps
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

inference llm model-compression pytorch quantization

Summary

AI summary

Add Triton fused Walsh‑Hadamard kernel for 5x faster inference and a GPU benchmark script.

Full changelog
  • Add Triton fused Walsh-Hadamard kernel for 5x faster inference (1.9 → 9.9 tok/s)
  • Cache Wscale/inv_resid_scale as Python floats to eliminate GPU→CPU sync per forward pass
  • Add GPU benchmark script (GLQ vs AWQ vs bf16): perplexity, tokens/sec, GPU memory, disk size
View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track Glq

Get notified when new releases ship.

Sign up free

About Glq

All releases →

Related context

Beta — feedback welcome: [email protected]