Alexander Whitestone 3172415da1
All checks were successful
Smoke Test / smoke (pull_request) Successful in 28s
feat: implement TurboQuant upstream watch monitoring system
- Add scripts/upstream_watch.py for monitoring upstream repositories
- Add .github/workflows/upstream-watch.yml for weekly automated monitoring
- Add docs/upstream-watch.md for documentation
- Add scripts/run_upstream_watch.sh for easy execution
- Add scripts/test_upstream_watch.py for testing

Addresses issue #15: [P4] Upstream llama.cpp / Ollama TurboQuant watch

Features:
1. Monitor llama.cpp, Ollama, and ggml repositories
2. Search for TurboQuant/PolarQuant/QJL keywords
3. Check issues, PRs, and release notes
4. Generate text and JSON reports
5. Weekly GitHub Action for continuous monitoring
6. Automated issue creation when findings detected

Usage:
- Run monitor: python3 scripts/upstream_watch.py --days 30
- JSON output: python3 scripts/upstream_watch.py --format json
- Weekly monitoring: GitHub Action runs every Monday at 9:00 AM UTC

When upstream lands:
1. Detection: Monitor will detect mentions
2. Evaluation: Compare upstream vs fork
3. Decision: Migrate if upstream is better

Closes #15
2026-04-14 22:40:18 -04:00
2026-03-30 17:08:45 +00:00
2026-03-30 21:06:49 +00:00
2026-03-30 13:11:45 -04:00

TurboQuant

KV cache compression for local inference on M4 Max MacBook Pro.

What

TurboQuant (Google, ICLR 2026) is a three-stage KV cache compression method:

  1. PolarQuant — WHT rotation + polar coordinates + Lloyd-Max codebook (~4.2x compression)
  2. QJL — 1-bit quantized Johnson-Lindenstrauss residual correction
  3. TurboQuant — PolarQuant + QJL = ~3.5 bits/channel, zero accuracy loss

Why

Unlock 64K-128K context on qwen3.5:27b within 32GB unified memory. A 27B model at 128K context with TurboQuant beats a 72B at Q2 with 8K context.

Status

See issues for current progress.

Roles

  • Strago: Build spec author
  • Cid: Implementation, benchmarks, deployment
  • Locke: Research support, upstream watch
  • John: Quality review
  • Frankie: Coordination

Source Repos

Docs

Description
TurboQuant KV cache compression for local inference — PolarQuant + QJL on M4 Max via llama.cpp/Ollama. Build spec from Strago, build by Cid, coordination by Frankie.
Readme MIT 28 MiB
Languages
Python 91.3%
C++ 5.7%
Metal 2.2%
CMake 0.8%