SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2511.04063 · NeurIPS · 2025

DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization

Jing Lin, Jian Cheng, Yiwu Yao, Yuantian Shao, Yuanteng Chen, Peisong Wang, Jianlin Yu, Zhihui Wei

arXiv · PDF · Open in the Atlas

Code that ran

6 of 16 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 10 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2511.04063.json · badge: /api/ran/2511.04063.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
CAS-CLab/DartQuant canonical (classifier label)
classifier basis: census
6 ran · 10 no recorded run
FunctionStatusWhere it lives
add_wrapper_after_function_call_in_method Ran
ran; our contract draft was wrong, not the code
CAS-CLab/DartQuant/NPU_DartQuant/fake_quant/monkeypatch.py
pointer only (licence: NONE) · get_code("e649cf99e1985c23")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, CAS-CLab/DartQuant when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

asym_dequant Ran
ran, honoured the contract we drafted
CAS-CLab/DartQuant/NPU_DartQuant/fake_quant/quant_utils.py
pointer only (licence: NONE) · get_code("0225f1f47f1347ae")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, CAS-CLab/DartQuant when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

asym_quant Ran
ran; our contract draft was wrong, not the code
CAS-CLab/DartQuant/NPU_DartQuant/fake_quant/quant_utils.py
pointer only (licence: NONE) · get_code("0979b095b9a8e5d5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, CAS-CLab/DartQuant when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

copy_func_with_new_globals Ran
ran; our contract draft was wrong, not the code
CAS-CLab/DartQuant/NPU_DartQuant/fake_quant/monkeypatch.py
pointer only (licence: NONE) · get_code("76b345bcf88c8668")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, CAS-CLab/DartQuant when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_minq_maxq Ran
ran, honoured the contract we drafted
CAS-CLab/DartQuant/NPU_DartQuant/fake_quant/quant_utils.py
pointer only (licence: NONE) · get_code("56fe9b504cdc9689")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, CAS-CLab/DartQuant when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_rope_function_name Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
CAS-CLab/DartQuant/NPU_DartQuant/fake_quant/model_utils.py
pointer only (licence: NONE) · get_code("8005fc23ccbe61fb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, CAS-CLab/DartQuant when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_c4_new Not yet run
unverified (harvested, no recorded run)
CAS-CLab/DartQuant/NPU_DartQuant/fake_quant/data_utils.py
pointer only (licence: NONE) · get_code("9b105523e5cc293f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, CAS-CLab/DartQuant when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_layers Not yet run
unverified (harvested, no recorded run)
CAS-CLab/DartQuant/NPU_DartQuant/fake_quant/model_utils.py
pointer only (licence: NONE) · get_code("eb59d0a73734e449")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, CAS-CLab/DartQuant when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_mutil_head_scale Not yet run
unverified (harvested, no recorded run)
CAS-CLab/DartQuant/NPU_DartQuant/calibrater/get_train_data.py
pointer only (licence: NONE) · get_code("738315ace19a8a3e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, CAS-CLab/DartQuant when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_per_channel_scale Not yet run
unverified (harvested, no recorded run)
CAS-CLab/DartQuant/NPU_DartQuant/calibrater/get_train_data.py
pointer only (licence: NONE) · get_code("b8790746f232537a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, CAS-CLab/DartQuant when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_ptb_new Not yet run
unverified (harvested, no recorded run)
CAS-CLab/DartQuant/NPU_DartQuant/fake_quant/data_utils.py
pointer only (licence: NONE) · get_code("3af6f58d0be0329f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, CAS-CLab/DartQuant when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_wikitext2 Not yet run
unverified (harvested, no recorded run)
CAS-CLab/DartQuant/NPU_DartQuant/fake_quant/data_utils.py
pointer only (licence: NONE) · get_code("8715ffbc2b65ebe5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, CAS-CLab/DartQuant when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

llama_2_70b_forward Not yet run
unverified (harvested, no recorded run)
CAS-CLab/DartQuant/NPU_DartQuant/fake_quant/eval_utils.py
pointer only (licence: NONE) · get_code("8c91192eb1f9602e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, CAS-CLab/DartQuant when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

model_type_extractor Not yet run
unverified (harvested, no recorded run)
CAS-CLab/DartQuant/NPU_DartQuant/fake_quant/model_utils.py
pointer only (licence: NONE) · get_code("cdd805f7fc7a0842")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, CAS-CLab/DartQuant when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

optimize_npu Not yet run
unverified (harvested, no recorded run)
CAS-CLab/DartQuant/NPU_DartQuant/calibrater/r1_base_qr.py
pointer only (licence: NONE) · get_code("60abacfad210e6fb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, CAS-CLab/DartQuant when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

ppl_evaluator Not yet run
unverified (harvested, no recorded run)
CAS-CLab/DartQuant/NPU_DartQuant/fake_quant/eval_utils.py
pointer only (licence: NONE) · get_code("9b07900fe82b07cb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, CAS-CLab/DartQuant when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 10 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 0 the same month, 8 later) and 6 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_rope_function_name 4 other papers
1 dated earlier, 3 later
2404.00456 (2024-04)
QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
2602.02546 (2026-02)
D 2 Quant: Accurate Low-bit Post-Training Weight Quantization for LLMs
2604.07955 (2026-04)
Rethinking Residual Errors in Compensation-based LLM Quantization
and 1 more not named here
get_layers 3 other papers
1 dated earlier, 2 later
2404.00456 (2024-04)
QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
2604.07955 (2026-04)
Rethinking Residual Errors in Compensation-based LLM Quantization
2605.15491 (2026-05)
Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs
model_type_extractor 3 other papers
1 dated earlier, 2 later
2404.00456 (2024-04)
QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
2604.07955 (2026-04)
Rethinking Residual Errors in Compensation-based LLM Quantization
2605.15491 (2026-05)
Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs
asym_dequant 2 other papers
1 dated earlier, 1 later
2410.09426 (2024-10)
FLATQUANT: Flatness Matters for LLM Quantization
2605.19660 (2026-05)
OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond
asym_quant 2 other papers
1 dated earlier, 1 later
2404.00456 (2024-04)
QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
2605.19660 (2026-05)
OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond
get_ptb_new 2 other papers
2 dated earlier
2501.13987 (2025-01)
OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting
2510.16292 (2025-10)
QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models
add_wrapper_after_function_call_in_method 1 other paper
1 later
2605.15491 (2026-05)
Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs
copy_func_with_new_globals 1 other paper
1 later
2605.15491 (2026-05)
Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs
get_minq_maxq 1 other paper
1 later
2602.02546 (2026-02)
D 2 Quant: Accurate Low-bit Post-Training Weight Quantization for LLMs
get_wikitext2 1 other paper
1 dated earlier
2510.16292 (2025-10)
QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Quantization plays a crucial role in accelerating the inference of large-scale models, and rotational matrices have been shown to effectively improve quantization performance by smoothing outliers. However, end-to-end fine-tuning of rotational optimization algorithms incurs high computational costs and is prone to overfitting. To address this challenge, we propose an efficient distribution-aware rotational calibration method, DartQuant, which reduces the complexity of rotational optimization by constraining the distribution of the activations after rotation. This approach also effectively reduces reliance on task-specific losses, thereby mitigating the risk of overfitting. Additionally, we introduce the QR-Orth optimization scheme, which replaces expensive alternating optimization with a more efficient solution. In a variety of model quantization experiments, DartQuant demonstrates superior performance. Compared to existing methods, it achieves 47× acceleration and 10× memory savings for rotational optimization on a 70B model. Furthermore, it is the first to successfully complete rotational calibration for a 70B model on a single 3090 GPU, making quantization of large language models feasible in resource-constrained environments. Code is available at https://github.com/CAS-CLab/DartQuant.git.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2511.04063")
get_code_for_paper("2511.04063")
have("2511.04063")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2511.04063.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2511.04063.svg)](https://syntology.ai/paper/2511.04063)

Connect an agent — have() is free.