Papers › FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning

FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning

30 Mar 2025arXiv:2503.23367archive 2025-07-28

Hang Guo, Yawei Li, Taolin Zhang, Jiangshan Wang, Tao Dai, Shu-Tao Xia, Luca Benini

Visual Autoregressive (VAR) modeling has gained popularity for its shift towards next-scale prediction. However, existing VAR paradigms process the entire token map at each scale step, leading to the complexity and runtime scaling dramatically with image resolution. To address this challenge, we propose FastVAR, a post-training acceleration method for efficient resolution scaling with VARs. Our key finding is that the majority of latency arises from the large-scale step where most tokens have already converged. Leveraging this observation, we develop the cached token pruning strategy that only forwards pivotal tokens for scale-specific modeling while using cached tokens from previous scale steps to restore the pruned slots. This significantly reduces the number of forwarded tokens and improves the efficiency at larger resolutions. Experiments show the proposed FastVAR can further speedup FlashAttention-accelerated VAR by 2.7× with negligible performance drop of <1%. We further extend FastVAR to zero-shot generation of higher resolution images. In particular, FastVAR can generate one 2K image with 15GB memory footprints in 1.5s on a single NVIDIA 3090 GPU. Code is available at https://github.com/csguoh/FastVAR.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2503.23367")

Code

Syntology Ran 3 of 14 code samples harvested from 1 repository linked to this paper; 11 have no recorded run. Of those that ran: 3 ran with no contract checked.

By repository: official repository: 14 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

csguoh/fastvar officialmentioned in papermentioned on GitHubpytorchMIT 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

14 samples harvested; 3 ran; 0 honoured the contract we drafted; 11 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran
11unverified

Licence: 0 of the 14 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 csguoh/fastvar. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

apply_rotary_emb csguoh/fastvar/Infinity/infinity/models/basic.py official repository ran MIT (permissive) · 42125baaa5c021b6 · report
get_dropout_layer csguoh/fastvar/Infinity/infinity/models/fastvar_basic.py official repository ran MIT (permissive) · b4a8295838aac5c1 · report
precompute_rope2d_freqs_grid csguoh/fastvar/Infinity/infinity/models/basic.py official repository ran MIT (permissive) · 94b02b98b65ce1b4 · report
apply_rotary_emb_fastvar csguoh/fastvar/Infinity/infinity/models/fastvar_basic.py official repository unverified MIT (permissive) · 9e16906b7f949f04 · report
compute_merge csguoh/fastvar/Infinity/infinity/models/fastvar_utils.py official repository unverified MIT (permissive) · bb07b7c6bc141e2d · report
compute_merge csguoh/fastvar/HART/hart/modules/networks/fastvar_utils.py official repository unverified MIT (permissive) · 974751f30ae5dccd · report
do_nothing csguoh/fastvar/Infinity/infinity/models/fastvar_utils.py official repository unverified MIT (permissive) · 942c492abe601d24 · report
features2image csguoh/fastvar/Infinity/infinity/models/bitwise_self_correction.py official repository unverified MIT (permissive) · 0a9d5c3882889998 · report
get_position_ids csguoh/fastvar/HART/hart/modules/networks/fastvar_basic.py official repository unverified MIT (permissive) · 9bd25e1e6d3188a3 · report
get_position_ids_1d csguoh/fastvar/HART/hart/modules/networks/fastvar_basic.py official repository unverified MIT (permissive) · 82c722b23631ab21 · report
labels2image csguoh/fastvar/Infinity/infinity/models/bitwise_self_correction.py official repository unverified MIT (permissive) · 9ba6c0e0e8e4e50e · report
masked_previous_scale_cache csguoh/fastvar/Infinity/infinity/models/fastvar_utils.py official repository unverified MIT (permissive) · a2661ae675e65815 · report
masked_previous_scale_cache csguoh/fastvar/HART/hart/modules/networks/fastvar_utils.py official repository unverified MIT (permissive) · c24fea416022c9ec · report
slow_attn csguoh/fastvar/HART/hart/modules/networks/fastvar_basic.py official repository unverified MIT (permissive) · f85408c04c9c626f · report

Tasks

2k

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Pruning

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