SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.11235 · NeurIPS · 2024

QTIP: Quantization with Trellises and Incoherence Processing

Christopher De Sa, Albert Tseng, Qingyao Sun, David Hou

arXiv · PDF · Open in the Atlas

Code that ran

6 of 8 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; 0 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 5 failures of our instrument; 2 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2406.11235.json · badge: /api/ran/2406.11235.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
Cornell-RelaxML/qtip canonical (classifier label)
classifier basis: classifier_2025
6 ran · 2 no recorded run
FunctionStatusWhere it lives
logits_to_probs Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Cornell-RelaxML/qtip/eval/interactive_gen.py
pointer only (licence: GPL-3.0) · get_code("357adcbb4430f3ab")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, Cornell-RelaxML/qtip, is not in the permissive set Syntology serves inline. 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.

check_exist Ran
ran, violated the contract we drafted
Cornell-RelaxML/qtip/quantize_llama/quantize_finetune_llama.py
pointer only (licence: GPL-3.0) · get_code("6a853f497a6fd273")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, Cornell-RelaxML/qtip, is not in the permissive set Syntology serves inline. 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.

decode_1mad Ran
ran; our contract draft was wrong, not the code
Cornell-RelaxML/qtip/lib/codebook/bitshift.py
pointer only (licence: GPL-3.0) · get_code("9e5bdf87180c4dfd")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, Cornell-RelaxML/qtip, is not in the permissive set Syntology serves inline. 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.

decode_2mad Ran
ran; our contract draft was wrong, not the code
Cornell-RelaxML/qtip/lib/codebook/bitshift.py
pointer only (licence: GPL-3.0) · get_code("d31d04a421745b56")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, Cornell-RelaxML/qtip, is not in the permissive set Syntology serves inline. 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.

decode_3inst Ran
ran; our contract draft was wrong, not the code
Cornell-RelaxML/qtip/lib/codebook/bitshift.py
pointer only (licence: GPL-3.0) · get_code("d425be1e34395d91")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, Cornell-RelaxML/qtip, is not in the permissive set Syntology serves inline. 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.

multinomial_sample_one_no_sync Ran
ran; our contract draft was wrong, not the code
Cornell-RelaxML/qtip/eval/interactive_gen.py
pointer only (licence: GPL-3.0) · get_code("0b5f90e8856ad7af")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, Cornell-RelaxML/qtip, is not in the permissive set Syntology serves inline. 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.

LDLQ Not yet run
unverified (harvested, no recorded run)
Cornell-RelaxML/qtip/lib/algo/ldlq.py
pointer only (licence: GPL-3.0) · get_code("12c8b07dea3d0c16")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, Cornell-RelaxML/qtip, is not in the permissive set Syntology serves inline. 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.

sample Not yet run
unverified (harvested, no recorded run)
Cornell-RelaxML/qtip/eval/interactive_gen.py
pointer only (licence: GPL-3.0) · get_code("ec366460d4db87bc")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, Cornell-RelaxML/qtip, is not in the permissive set Syntology serves inline. 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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 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
multinomial_sample_one_no_sync 8 other papers
4 dated earlier, 4 later
2212.04356 (2022-12)
Robust Speech Recognition via Large-Scale Weak Supervision
2306.05284 (2023-06)
Simple and Controllable Music Generation
2308.02560 (2023-08)
From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusion
and 5 more not named here
logits_to_probs 5 other papers
1 dated earlier, 4 later
2402.04396 (2024-02)
QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks
2408.07092 (2024-08)
Post-Training Sparse Attention with Double Sparsity
2408.14690 (2024-08)
Training-Free Activation Sparsity in Large Language Models
and 2 more not named here

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

Post-training quantization (PTQ) reduces the memory footprint of LLMs by quantizing weights to low-precision datatypes. Since LLM inference is usually memorybound, PTQ methods can improve inference throughput. Recent state-of-the-art PTQ approaches use vector quantization (VQ) to quantize multiple weights at once, which improves information utilization through better shaping. However, VQ requires a codebook with size exponential in the dimension. This limits current VQbased PTQ works to low VQ dimensions (≤ 8) that in turn limit quantization quality. Here, we introduce QTIP, which instead uses trellis coded quantization (TCQ) to achieve ultra-high-dimensional quantization. TCQ uses a stateful decoder that separates the codebook size from the bitrate and effective dimension. QTIP introduces a spectrum of lookup-only to computed lookup-free trellis codes designed for a hardware-efficient "bitshift" trellis structure; these codes achieve state-of-theart results in both quantization quality and inference speed.

For agents

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

get_harvested_code_for_paper("2406.11235")
get_code_for_paper("2406.11235")
have("2406.11235")

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

curl https://syntology.ai/api/ran/2406.11235.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.11235.svg)](https://syntology.ai/paper/2406.11235)

Connect an agent — have() is free.