SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.06082 · 2024

FrameQuant: Flexible Low-Bit Quantization for Transformers

arXiv · PDF · Open in the Atlas

Code that ran

12 of 18 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; 1 honoured the contract we drafted, 1 violated it and 1 has no contract verdict; 9 failures of our instrument; 6 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2403.06082.json · badge: /api/ran/2403.06082.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
vsingh-group/framequant canonical (classifier label)
classifier basis: census
12 ran · 6 no recorded run
FunctionStatusWhere it lives
array_code_gen Ran
ran; our contract draft was wrong, not the code
vsingh-group/framequant/fast-hadamard-transform/csrc/code_gen.py
pointer only (licence: NONE) · get_code("5e48070287726d38")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vsingh-group/framequant 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.

construct_real_tff Ran
ran; our contract draft was wrong, not the code
vsingh-group/framequant/utils/construct_tff.py
pointer only (licence: NONE) · get_code("04cf3834e0e305e6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vsingh-group/framequant 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.

construct_tight_frames Ran
ran on a synthesized input
vsingh-group/framequant/utils/construct_tff.py
pointer only (licence: NONE) · get_code("decbe159fea96172")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vsingh-group/framequant 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.

find_layers Ran
ran; our contract draft was wrong, not the code
vsingh-group/framequant/modelutils.py
pointer only (licence: NONE); the stored copy get_code serves, from squeezeailab/kvquant, is pointer only (licence: NONE) · get_code("a9e7f2cdf016b88b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vsingh-group/framequant 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.

llama_eval Ran
ran; our contract draft was wrong, not the code
vsingh-group/framequant/utils/eval_utils.py
pointer only (licence: NONE) · get_code("0f5810ef333bc3dc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vsingh-group/framequant 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.

load_llama_from_config Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
vsingh-group/framequant/inference.py
pointer only (licence: NONE) · get_code("9f18bcbf55043e12")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vsingh-group/framequant 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.

profile Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
vsingh-group/framequant/packbit/kernel.py
pointer only (licence: NONE) · get_code("7e27a0f1e3ced11b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vsingh-group/framequant 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.

quantize Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
vsingh-group/framequant/quant.py
pointer only (licence: NONE) · get_code("ff8ffe5499b035fb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vsingh-group/framequant 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.

quantize_float_bias Ran
ran; our contract draft was wrong, not the code
vsingh-group/framequant/quant.py
pointer only (licence: NONE) · get_code("80cef67ba93a9352")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vsingh-group/framequant 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.

quantize_int_bias Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
vsingh-group/framequant/quant.py
pointer only (licence: NONE) · get_code("c36798d3ae59a462")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vsingh-group/framequant 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.

string_to_array Ran
ran, honoured the contract we drafted
vsingh-group/framequant/fast-hadamard-transform/csrc/code_gen.py
pointer only (licence: NONE) · get_code("d4a256fbc9029891")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vsingh-group/framequant 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.

tffet Ran
ran, violated the contract we drafted
vsingh-group/framequant/utils/construct_tff.py
pointer only (licence: NONE) · get_code("4c72411332a6c17d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vsingh-group/framequant 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 Not yet run
unverified (harvested, no recorded run)
vsingh-group/framequant/datautils.py
pointer only (licence: NONE) · get_code("4d29e98e5f0e4149")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vsingh-group/framequant 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_llama Not yet run
unverified (harvested, no recorded run)
vsingh-group/framequant/llama.py
pointer only (licence: NONE) · get_code("7ca52cb5d1719b2f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vsingh-group/framequant 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 Not yet run
unverified (harvested, no recorded run)
vsingh-group/framequant/datautils.py
pointer only (licence: NONE) · get_code("3265f727a396f15d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vsingh-group/framequant 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)
vsingh-group/framequant/datautils.py
pointer only (licence: NONE) · get_code("ab19b8a72ceae217")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vsingh-group/framequant 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_pack3 Not yet run
unverified (harvested, no recorded run)
vsingh-group/framequant/llama.py
pointer only (licence: NONE) · get_code("effa493c10026adc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vsingh-group/framequant 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.

load_quant Not yet run
unverified (harvested, no recorded run)
vsingh-group/framequant/inference.py
pointer only (licence: NONE) · get_code("e6ca4726f327dc2c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vsingh-group/framequant 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 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 3 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 3 later) and 15 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
find_layers 27 other papers
11 dated earlier, 1 the same month, 13 later, 1 same year, order not determinable, 1 undated
2203.13474 (2022-03)
CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis
2023.emnlp-main.892 (2023 (year only))
Z-FOLD: A Frustratingly Easy Post-Training Quantization Scheme for LLMs
2307.09288 (2023-07)
Llama 2: Open Foundation and Fine-Tuned Chat Models
and 24 more not named here
array_code_gen 1 other paper
1 later
2606.10520 (2026-06)
UniSVQ: 2-bit Unified Scalar-Vector Quantization
string_to_array 1 other paper
1 later
2606.10520 (2026-06)
UniSVQ: 2-bit Unified Scalar-Vector Quantization

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

Transformers are the backbone of powerful foundation models for many Vision and Natural Language Processing tasks. But their compute and memory/storage footprint is large, and so, serving such models is expensive often requiring high-end hardware. To mitigate this difficulty, Post-Training Quantization seeks to modify a pre-trained model and quantize it to eight bits or lower, significantly boosting compute/memory/latency efficiency. Such models have been successfully quantized to four bits with some performance loss. In this work, we outline a simple scheme to quantize Transformer-based models to just two bits (plus some overhead) with only a small drop in accuracy. Key to our formulation is a concept borrowed from Harmonic analysis called Fusion Frames. Our main finding is that the quantization must take place not in the original weight space, but instead in the Fusion Frame representations. If quantization is interpreted as the addition of noise, our casting of the problem allows invoking an extensive body of known consistent recovery and noise robustness guarantees. Further, if desired, de-noising filters are known in closed form. We show empirically, via a variety of experiments, that (almost) two-bit quantization for Transformer models promises sizable efficiency gains. The code is available at https://github.com/vsingh-group/FrameQuant

For agents

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

get_harvested_code_for_paper("2403.06082")
get_code_for_paper("2403.06082")
have("2403.06082")

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

curl https://syntology.ai/api/ran/2403.06082.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.06082.svg)](https://syntology.ai/paper/2403.06082)

Connect an agent — have() is free.