Papers › Training-Free Activation Sparsity in Large Language Models

Training-Free Activation Sparsity in Large Language Models

26 Aug 2024arXiv:2408.14690archive 2025-07-28

James Liu, Pragaash Ponnusamy, Tianle Cai, Han Guo, Yoon Kim, Ben Athiwaratkun

Activation sparsity can enable practical inference speedups in large language models (LLMs) by reducing the compute and memory-movement required for matrix multiplications during the forward pass. However, existing methods face limitations that inhibit widespread adoption. Some approaches are tailored towards older models with ReLU-based sparsity, while others require extensive continued pre-training on up to hundreds of billions of tokens. This paper describes TEAL, a simple training-free method that applies magnitude-based activation sparsity to hidden states throughout the entire model. TEAL achieves 40-50% model-wide sparsity with minimal performance degradation across Llama-2, Llama-3, and Mistral families, with sizes varying from 7B to 70B. We improve existing sparse kernels and demonstrate wall-clock decoding speed-ups of up to 1.53× and 1.8× at 40% and 50% model-wide sparsity. TEAL is compatible with weight quantization, enabling further efficiency gains.

PaperPDFCodeCode 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.

Syntology holds a reference implementation of TEAL, generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='TEAL') (how to connect); the free check have('2408.14690') needs no token.

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

Code

Syntology 14 code samples harvested from 1 repository linked to this paper: 7 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; 5 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 7 ran (2 with no instrument failure; 5 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. 3 of the 7 samples that ran have no recorded date.

fasterdecoding/teal officialmentioned in papermentioned on GitHubpytorchSyntology: 14 samples, 7 ran (5 instrument-failed) · 7 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

14 samples harvested: 7 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; 5 where Syntology's instrument failed) · 7 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; the contract check could not run
2ran
7unverified

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 fasterdecoding/teal. “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.

fasterdecoding/teal official repository 14 samples, 7 ran (5 instrument-failed) · 7 unverified
ActivationModule teal/model.py ran MIT (permissive) · 4f283dcb0a0422d7 · report fixture: returned ActivationModule · level recorded 2026-09-22
Distribution in 5 papers teal/model.py ran MIT (permissive) · c5354bfc34cf09a3 · report fixture: returned Distribution · level recorded 2026-09-22
get_layer_greedy_sparsities teal/model.py ran · our draft was wrong MIT (permissive) · 9b77813d7a7d746d · report fixture: signature layer_sparsities:list/1/float, results_dir:str/0/str · returned dict · level recorded 2026-09-22
interp in 22 papers teal/model.py ran · our draft was wrong MIT (permissive) · e141b830083564c0 · report fixture: signature x:Tensor/1/float, xp:Tensor/1/float, fp:Tensor/1/float · returned Tensor · level recorded 2026-09-22
logits_to_probs in 18 papers gpt-fast/generate.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · f4d39ec8a89dcfa0 · report fixture: signature logits:Tensor/2/float, temperature:float/0/float, top_k:NoneType/0/? · returned Tensor · level recorded, date not recorded
multinomial_sample_one_no_sync in 10 papers gpt-fast/generate.py ran · our draft was wrong fingerprinted MIT (permissive) · 5b6f45360aa68edd · report fixture: signature probs_sort:Tensor/2/float · returned Tensor · level recorded, date not recorded
sample in 167 papers
census: 8 implementations from 9 papers, 7 distinct outputs across 5 buckets, one shared input per bucket
gpt-fast/generate.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic fingerprinted MIT (permissive) · 8465782fc7e1fe39 · report fixture: signature logits:Tensor/3/float, temperature:float/0/float, top_k:NoneType/0/? · returned tuple · level recorded, date not recorded
SparseModelMixin teal/model.py unverified MIT (permissive) · dc1705f0ac812a98 · report
SparsifyFn teal/model.py unverified MIT (permissive) · 8247ca701a965ec3 · report
_FA2_forward teal/model.py unverified MIT (permissive) · 82f026ca4d133e3f · report
_mlp_forward teal/model.py unverified MIT (permissive) · 8f9f6dcb910a3d1e · report
_monkeypatch_layer teal/model.py unverified MIT (permissive) · 9d238e7c8da0339a · report
_monkeypatch_mlp teal/model.py unverified MIT (permissive) · 31cd3abe1ae1c21e · report
_monkeypatch_self_attn teal/model.py unverified MIT (permissive) · f89bf27e96be35db · 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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. 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. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

2 assemblies on this paper: 1 harvested, 1 generated.

generated Assembly for TEAL (graph method: TEAL), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 4 property tests passed on both).

label matches by construction: the code was generated for this method (not judged by a model)

  1. compute_sparsification_error entry · level 3 · ran · honoured contract · eb53921be29dcd8d4b023dce66a00bff71ac8728434d6ef38ac53998d720e20a

harvested Assembly for TEAL (graph method: TEAL). 12 bricks; individually on a fixture: 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) · 7 unverified. The assembly has not been run end-to-end.

  1. SparseModelMixin entry · level 0 · unverified · dc1705f0ac812a98
  2. _monkeypatch_layer helper · level 0 · unverified · 9d238e7c8da0339a
  3. get_layer_greedy_sparsities helper · level 1 · ran · our draft was wrong · 9b77813d7a7d746d
  4. _monkeypatch_mlp helper · level 0 · unverified · 31cd3abe1ae1c21e
  5. _monkeypatch_self_attn helper · level 0 · unverified · f89bf27e96be35db
  6. ActivationModule helper · level 1 · ran · 4f283dcb0a0422d7
  7. Distribution helper · level 1 · ran · c5354bfc34cf09a3
  8. SparsifyFn helper · level 0 · unverified · 8247ca701a965ec3
  9. _mlp_forward helper · level 0 · unverified · 8f9f6dcb910a3d1e
  10. get_module_device helper · level 1 · ran · our draft was wrong · f8ef5ca2539fcee5
  11. _FA2_forward helper · level 0 · unverified · 82f026ca4d133e3f
  12. interp helper · level 1 · ran · our draft was wrong · e141b830083564c0

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="2408.14690") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Quantization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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