Papers › TaQ-DiT: Time-aware Quantization for Diffusion Transformers

TaQ-DiT: Time-aware Quantization for Diffusion Transformers

21 Nov 2024arXiv:2411.14172archive 2025-07-28

Xinyan Liu, Huihong Shi, Yang Xu, Zhongfeng Wang

Transformer-based diffusion models, dubbed Diffusion Transformers (DiTs), have achieved state-of-the-art performance in image and video generation tasks. However, their large model size and slow inference speed limit their practical applications, calling for model compression methods such as quantization. Unfortunately, existing DiT quantization methods overlook (1) the impact of reconstruction and (2) the varying quantization sensitivities across different layers, which hinder their achievable performance. To tackle these issues, we propose innovative time-aware quantization for DiTs (TaQ-DiT). Specifically, (1) we observe a non-convergence issue when reconstructing weights and activations separately during quantization and introduce a joint reconstruction method to resolve this problem. (2) We discover that Post-GELU activations are particularly sensitive to quantization due to their significant variability across different denoising steps as well as extreme asymmetries and variations within each step. To address this, we propose time-variance-aware transformations to facilitate more effective quantization. Experimental results show that when quantizing DiTs' weights to 4-bit and activations to 8-bit (W4A8), our method significantly surpasses previous quantization methods.

PaperPDFCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 7 code samples harvested from 1 repository linked to this paper: 5 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: found in paper text by Syntology: 7 samples from 1 repository, 5 ran (2 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

6xy-liu/Taq-DiT found in paper text by SyntologySyntology: 7 samples, 5 ran (3 instrument-failed) · 2 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

7 samples harvested: 5 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
2ran
2unverified

Licence: 7 of the 7 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 6xy-liu/Taq-DiT. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

6xy-liu/Taq-DiT found in paper text by Syntology 7 samples, 5 ran (3 instrument-failed) · 2 unverified
ObserverBase quant/quantization/fake_quant.py ran · metamorphic tier: deterministic no licence file found · pointer only · 119e117e97e53371 · report fixture: returned ObserverBase · level recorded 2026-09-22
QuantizeBase quant/quantization/fake_quant.py ran · metamorphic tier: deterministic no licence file found · pointer only · f352d07e60e42108 · report fixture: returned QuantizeBase · level recorded 2026-09-22
fake_quantize_learnable_per_channel_affine_training quant/quantization/fake_quant.py ran · our draft was wrong fingerprinted no licence file found · pointer only · ba1ffd12796f5219 · report fixture: signature x:Tensor/4/float, scale:Tensor/1/float, zero_point:Tensor/1/int, ch_axis:int/0/int, quant_min:int/0/int, quant_max:int/0/int, grad_factor:float/0/float · returned Tensor · level recorded 2026-09-22
fake_quantize_learnable_per_tensor_affine_training quant/quantization/fake_quant.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 9eaea08ad40b7c03 · report fixture: signature x:Tensor/2/float, scale:Tensor/0/float, zero_point:Tensor/0/int, quant_min:int/0/int, quant_max:int/0/int, grad_factor:float/0/float · returned Tensor · level recorded 2026-09-22
grad_scale in 16 papers
census: 3 implementations from 8 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 2, kind float, dtype float32
quant/quantization/fake_quant.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 043c3be8a95e065c · report fixture: signature t:Tensor/2/float, scale:float/0/float · returned Tensor · level recorded 2026-09-22
LSQFakeQuantize quant/quantization/fake_quant.py unverified no licence file found · pointer only · 5f945957d82c3552 · report
global_val quant/quantization/fake_quant.py unverified no licence file found · pointer only · 47345a9d948debda · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for TaQ-DiT (graph method: TaQ-DiT). 8 bricks; individually on a fixture: 6 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

  1. LSQFakeQuantize entry · level 0 · unverified · 5f945957d82c3552
  2. QuantizeBase helper · level 1 · ran · f352d07e60e42108
  3. fake_quantize_learnable_per_channel_affine_training helper · level 1 · ran · our draft was wrong · ba1ffd12796f5219
  4. fake_quantize_learnable_per_tensor_affine_training helper · level 1 · ran · our draft was wrong · 9eaea08ad40b7c03
  5. global_val helper · level 0 · unverified · 47345a9d948debda
  6. ObserverBase helper · level 1 · ran · 119e117e97e53371
  7. grad_scale helper · level 1 · ran · our draft was wrong · 043c3be8a95e065c
  8. round_ste helper · level 2 · ran · our draft was wrong · 675da8641c602b03

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2411.14172") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DenoisingModel CompressionQuantizationVideo Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DiffusionSPEED

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections