QuaNAG

Official implementation of QuaNAG: LLM-driven Memory-bounded Neural Architecture Generation via Quantization-branched Exploration

pyq623/QuaNAG

View on GitHub ↗

Official implementation of QuaNAG: LLM-driven Memory-bounded Neural Architecture Generation via Quantization-branched Exploration

QuaNAG grew -0.5% in the last 30 days, ranks 264th of 370 in Training Toolkits, last commit 85 days ago.

Star trajectory

68 days tracked
2026-09-14194 stars today2026-11-22
Momentum

-0.5% in 30d, below the Training Toolkits median of +0.3%.

Maintenance

Last commit 85 days ago, fresher than the median of 199.5d.

How it compares in Training Toolkits

QuaNAG
194
stars
-0.5% 30d
commit 85 days ago
Training Toolkits median
320
stars
+0.3% 30d
commit ~199.5d ago
Leader · TTS
46.3k
stars
+0.3% 30d
commit 827 days ago

Ranked 264th of 370 by stars.

Ranked by shared tags, then keywords, then stars
  1. Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.

    +43 (+2.4%) in 30d · Committed 2d ago · Python · Other license

    Shares Model Optimization, Training Toolkits

  2. Official implementation of Half-Quadratic Quantization (HQQ)

    +3 (+0.3%) in 30d · Committed 268d ago · Python · Apache-2.0

    Shares Model Optimization, Training Toolkits

  3. [EMNLP 2024 & AAAI 2026] A powerful toolkit for compressing large models including LLMs, VLMs, and video…

    +4 (+0.5%) in 30d · Committed 191d ago · Python · Apache-2.0

    Shares Model Optimization, Training Toolkits

  4. Runtime behavioral ablation for compressed LLMs. First target: Ternary Bonsai 2 27B — no weight modification…

    +11 (+1.9%) in 30d · Committed 60d ago · Python · Other license

    Shares Model Optimization, Training Toolkits

  5. 🦖 X—LLM: Cutting Edge & Easy LLM Finetuning

    -1 (-0.2%) in 30d · Committed 2d ago · Python · Apache-2.0

    Shares Training Toolkits, Model Optimization

  6. APOLLO: SGD-like Memory, AdamW-level Performance; MLSys'25 Oustanding Paper Honorable Mention

    +1 (+0.3%) in 30d · Committed 358d ago · Python · Other license

    Shares Training Toolkits, Model Optimization

  7. Quantized LLM training in pure CUDA/C++.

    +3 (+1.1%) in 30d · Committed 8d ago · C++ · Apache-2.0

    Shares Training Toolkits, Model Optimization

  8. Developer Hub for NVIDIA Alpamayo, containing ready-to-use recipes for fine-tuning, reinforcement-learning…

    +30 (+14%) in 30d · Committed 11d ago · Python · Apache-2.0

    Shares Training Toolkits, Model Optimization

  9. A collection of tricks and tools to speed up transformer models

    +2 (+0.9%) in 30d · Committed 40d ago · TeX · MIT

    Shares Training Toolkits, Model Optimization

  10. SpectralQuant: Calibrated Eigenbasis Rotation and Water-Filled Bit Allocation for KV-Cache Compression

    +0 (+0.0%) in 30d · Committed 190d ago · Python · MIT

    Shares Model Optimization, Training Toolkits

Language
Python
License
-
Contributors
1
Forks
3
Watchers
0
Open issues
0
Releases
0
Created
2026-08-28
Stars this week
-1

You've seen where QuaNAG stands today.

Get the moves before everyone else: the 5 Training Toolkits repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain QuaNAG?

Claim this page to add your own call-to-action.

Claim this page