SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.00774 · 2023

SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot

arXiv · PDF · Open in the Atlas

Code that ran

9 of 12 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, 0 violated it and 7 have no contract verdict; 2 failures of our instrument; 3 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/2301.00774.json · badge: /api/ran/2301.00774.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
ist-daslab/sparsegpt canonical (classifier label)
classifier basis: classifier_2025
1 ran · 2 no recorded run
nvidia/tensorrt-model-optimizer community (classifier label)
classifier basis not recorded on the link
7 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
get_bloom Ran
ran; our contract draft was wrong, not the code
ist-daslab/sparsegpt/bloom.py
code served (permissive licence) · get_code("cd666c16d4aaa66d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned MockBloomForCausalLM. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from unittest.mock import Mock, patch
import sys

torch.manual_seed(0)

# Mock the transformers library to avoid actual model downloads
class MockBloomForCausalLM:
    def __init__(self, *args, **kwargs):
        self.seqlen = None
    
    @classmethod
    def from_pretrained(cls, model_name, torch_dtype=None):
        return cls()

# Create a mock module for transformers
mock_transformers = Mock()
mock_transformers.BloomForCausalLM = MockBloomForCausalLM

# Patch transformers before the function is called
sys.modules['transformers'] = mock_transformers

ARGS = {
    'model': 'bigscience/bloom-560m'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch, transformers — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MockBloomForCausalLM — a MockBloomForCausalLM output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MockBloomForCausalLM output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_language_model_from_vl Ran
ran on a synthesized input
nvidia/tensorrt-model-optimizer/modelopt/torch/export/model_utils.py
pointer only (licence: Apache-2.0) · get_code("f1c26f01bf2f39a9")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, nvidia/tensorrt-model-optimizer, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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_model_type Ran
ran on a synthesized input
nvidia/tensorrt-model-optimizer/modelopt/torch/export/model_utils.py
pointer only (licence: Apache-2.0) · get_code("bc6cfb190b953479")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, nvidia/tensorrt-model-optimizer, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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_opt Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from IST-DASLab/gptq
pointer only · get_code("887f43fe08a6472d")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

is_multimodal_model Ran
ran on a synthesized input
nvidia/tensorrt-model-optimizer/modelopt/torch/export/model_utils.py
pointer only (licence: Apache-2.0) · get_code("140c6ce5087cbbce")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, nvidia/tensorrt-model-optimizer, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

pad_weights Ran
ran on a synthesized input
nvidia/tensorrt-model-optimizer/modelopt/torch/export/trtllm/model_config_utils.py
pointer only (licence: Apache-2.0) · get_code("f36d24bde785f7cc")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, nvidia/tensorrt-model-optimizer, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

prepare_enc_dec_export_dir Ran
ran on a synthesized input
nvidia/tensorrt-model-optimizer/modelopt/torch/export/trtllm/tensorrt_llm_utils.py
pointer only (licence: Apache-2.0) · get_code("e9eca650c1a383f2")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, nvidia/tensorrt-model-optimizer, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

student_input_bypass_fwd_hook Ran
ran on a synthesized input
nvidia/tensorrt-model-optimizer/modelopt/torch/distill/layerwise_distillation_model.py
pointer only (licence: Apache-2.0) · get_code("e3133ddfe52e03a0")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, nvidia/tensorrt-model-optimizer, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

svd Ran
ran on a synthesized input
nvidia/tensorrt-model-optimizer/modelopt/torch/quantization/model_calib.py
pointer only (licence: Apache-2.0) · get_code("54d01cbd62cf758a")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, nvidia/tensorrt-model-optimizer, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

bloom_sequential Not yet run
unverified (harvested, no recorded run)
ist-daslab/sparsegpt/bloom.py
code served (permissive licence) · get_code("5076786563dd8499")
How it ran

no invocation recorded.

opt_sequential Not yet run
unverified (harvested, no recorded run)
ist-daslab/sparsegpt/opt.py
code served (permissive licence) · get_code("bf403ae47e912dc1")
How it ran

no invocation recorded.

postprocess_amax Not yet run
unverified (harvested, no recorded run)
nvidia/tensorrt-model-optimizer/modelopt/torch/quantization/model_quant.py
pointer only (licence: Apache-2.0) · get_code("1c19ab0c6ad9a45c")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, nvidia/tensorrt-model-optimizer, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 4 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 4 later) and 8 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_bloom 5 other papers
5 later
2307.15290 (2023-07)
ChatHome: Development and Evaluation of a Domain-Specific Language Model for Home Renovation
2310.09499 (2023-10)
One-Shot Sensitivity-Aware Mixed Sparsity Pruning for Large Language Models
2024.findings-naacl.145 (2024 (year only))
Role Prompting Guided Domain Adaptation with General Capability Preserve for Large Language Models
and 2 more not named here
get_opt 5 other papers
1 dated earlier, 4 later
2210.17323 (2022-10)
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
2307.13304 (2023-07)
QuIP: 2-Bit Quantization of Large Language Models With Guarantees
2406.05981 (2024-06)
ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization
and 2 more not named here
bloom_sequential 2 other papers
2 later
2310.09499 (2023-10)
One-Shot Sensitivity-Aware Mixed Sparsity Pruning for Large Language Models
2025.findings-emnlp.1054 (2025 (year only))
Beyond Fixed-Length Calibration for Post-Training Compression of LLMs
opt_sequential 1 other paper
1 later
2025.findings-emnlp.1054 (2025 (year only))
Beyond Fixed-Length Calibration for Post-Training Compression of LLMs

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

We show for the first time that large-scale generative pretrained transformer (GPT) family models can be pruned to at least 50% sparsity in one-shot, without any retraining, at minimal loss of accuracy. This is achieved via a new pruning method called SparseGPT, specifically designed to work efficiently and accurately on massive GPT-family models. We can execute SparseGPT on the largest available open-source models, OPT-175B and BLOOM-176B, in under 4.5 hours, and can reach 60% unstructured sparsity with negligible increase in perplexity: remarkably, more than 100 billion weights from these models can be ignored at inference time. SparseGPT generalizes to semi-structured (2:4 and 4:8) patterns, and is compatible with weight quantization approaches. The code is available at: https://github.com/IST-DASLab/sparsegpt.

For agents

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

get_harvested_code_for_paper("2301.00774")
get_code_for_paper("2301.00774")
have("2301.00774")

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

curl https://syntology.ai/api/ran/2301.00774.json

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

[![Syntology run record](https://syntology.ai/api/ran/2301.00774.svg)](https://syntology.ai/paper/2301.00774)

Connect an agent — have() is free.