pith:APEUIO7K
On-the-Fly Adaptation to Quantization: Configuration-Aware LoRA for Efficient Fine-Tuning of Quantized LLMs
A single configuration-aware model generates effective LoRA adjustments for any quantization setting of an LLM without retraining per configuration.
arxiv:2509.25214 v4 · 2025-09-22 · cs.LG · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{APEUIO7KERA7QI6KETHDBSG7PG}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
CoA-LoRA dynamically adjusts the LoRA adapter to arbitrary quantization configurations without requiring repeated fine-tuning and achieves comparable or superior performance to state-of-the-art methods that fine-tune a separate LoRA adapter for each configuration.
The configuration-aware model can accurately predict low-rank adjustments for unseen quantization configurations when trained only on a Pareto-selected subset of configurations that cover different total bit-width budgets.
CoA-LoRA trains a single configuration-aware model on a Pareto-optimized set of quantization configurations to enable dynamic LoRA adaptation to arbitrary bit-width assignments without per-configuration fine-tuning.
Formal links
Cited by
Receipt and verification
| First computed | 2026-06-23T02:13:17.155161Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
03c9443bea2441f823ca24ce30c8df799aa0bf2c6c6c0e9893e7f142c1c48b75
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/APEUIO7KERA7QI6KETHDBSG7PG \
| jq -c '.canonical_record' \
| python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 03c9443bea2441f823ca24ce30c8df799aa0bf2c6c6c0e9893e7f142c1c48b75
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "206675ea5466bbc53114fd921373a1cf2f9c685a2a656bca4697848b74d6ecc9",
"cross_cats_sorted": [
"cs.AI"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.LG",
"submitted_at": "2025-09-22T11:07:50Z",
"title_canon_sha256": "abbfc27828e4645993eee55e963cc2ba42e476eabf42094228462acdad3626c7"
},
"schema_version": "1.0",
"source": {
"id": "2509.25214",
"kind": "arxiv",
"version": 4
}
}