Papers › ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less...

ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization

10 Jun 2024arXiv:2406.05981archive 2025-07-28

Haoran You, Yipin Guo, Yichao Fu, Wei Zhou, Huihong Shi, Xiaofan Zhang, Souvik Kundu, Amir Yazdanbakhsh, Yingyan Celine Lin

Large language models (LLMs) have shown impressive performance on language tasks but face challenges when deployed on resource-constrained devices due to their extensive parameters and reliance on dense multiplications, resulting in high memory demands and latency bottlenecks. Shift-and-add reparameterization offers a promising solution by replacing costly multiplications with hardware-friendly primitives in both the attention and multi-layer perceptron (MLP) layers of an LLM. However, current reparameterization techniques require training from scratch or full parameter fine-tuning to restore accuracy, which is resource-intensive for LLMs. To address this, we propose accelerating pretrained LLMs through post-training shift-and-add reparameterization, creating efficient multiplication-free models, dubbed ShiftAddLLM. Specifically, we quantize each weight matrix into binary matrices paired with group-wise scaling factors. The associated multiplications are reparameterized into (1) shifts between activations and scaling factors and (2) queries and adds according to the binary matrices. To reduce accuracy loss, we present a multi-objective optimization method to minimize both weight and output activation reparameterization errors. Additionally, based on varying sensitivity across layers to reparameterization, we develop an automated bit allocation strategy to further reduce memory usage and latency. Experiments on five LLM families and eight tasks consistently validate the effectiveness of ShiftAddLLM, achieving average perplexity improvements of 5.6 and 22.7 points at comparable or lower latency compared to the most competitive quantized LLMs at 3 and 2 bits, respectively, and more than 80% memory and energy reductions over the original LLMs. Codes and models are available at https://github.com/GATECH-EIC/ShiftAddLLM.

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 ShiftAddLLM, 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='ShiftAddLLM') (how to connect); the free check have('2406.05981') needs no token.

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

Code

Syntology 17 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 1 repository, 9 ran (3 with no instrument failure; 6 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 9 samples that ran have no recorded date.

gatech-eic/shiftaddllm officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 17 samples, 9 ran (6 instrument-failed) · 8 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

17 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

6ran · our draft was wrong
3ran
8unverified

Licence: 1 of the 17 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from gatech-eic/shiftaddllm. “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.

gatech-eic/shiftaddllm official repository 17 samples, 9 ran (6 instrument-failed) · 8 unverified
find_layers in 68 papers modelutils.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · a9e7f2cdf016b88b · report fixture: signature module:callable/0/?, layers:list/1/callable, name:str/0/str · returned dict · level recorded 2026-09-22
get_bloom in 8 papers model/bloom.py ran · our draft was wrong Apache-2.0 (permissive) · cd666c16d4aaa66d · report fixture: signature model:str/0/str · returned MockBloomForCausalLM · level recorded 2026-09-22
get_gemma model/gemma.py ran · our draft was wrong Apache-2.0 (permissive) · 62ed73ff09377dd3 · report fixture: signature model:str/0/str · returned MockGemmaForCausalLM · level recorded 2026-09-24
get_llama in 21 papers llama_analysis.py ran · our draft was wrong Apache-2.0 (permissive) · 88d590323ed219c8 · report fixture: signature model:str/0/str · returned MockLlamaForCausalLM · level recorded, date not recorded
get_mistral model/mistral.py ran · our draft was wrong Apache-2.0 (permissive) · 6fcbba51d98ff415 · report fixture: signature model:str/0/str · returned MockMistralForCausalLM · level recorded 2026-09-24
get_op energy/shiftaddllm_energy.py ran Apache-2.0 (permissive) · 533eb4023e30e110 · report fixture: signature input:int/0/int, output:int/0/int, bits:int/0/int, OPtype:str/0/str, name:str/0/str, batch:int/0/int · returned dict · level recorded 2026-09-24
get_op_list energy/shiftaddllm_energy.py ran Apache-2.0 (permissive) · 0b1b3174ad5e276b · report fixture: signature model_type:str/0/str, quant_type:str/0/str, dim:int/0/int, fc_dim:int/0/int, wbits:int/0/int · returned list · level recorded 2026-09-24
get_opt in 11 papers model/opt.py ran · our draft was wrong Apache-2.0 (permissive) · 887f43fe08a6472d · report fixture: signature model:str/0/str · returned MockOPTForCausalLM · level recorded, date not recorded
get_quant_op energy/shiftaddllm_energy.py ran Apache-2.0 (permissive) · 207a7b902ad10794 · report fixture: signature input:int/0/int, output:int/0/int, bits:int/0/int, quant_type:str/0/str · returned list · level recorded 2026-09-24
bloom_pack3 model/bloom.py unverified Apache-2.0 (permissive) · 0cad9f7e67e39610 · report
gemma_pack3 model/gemma.py unverified Apache-2.0 (permissive) · 8de8396130cd1a7d · report
get_c4 in 41 papers datautils.py unverified Apache-2.0 (permissive) · 3b7f82daf1a2f6d5 · report
get_ptb in 43 papers datautils.py unverified Apache-2.0 (permissive) · 7f7c3deb52669856 · report
get_wikitext2 in 78 papers datautils.py unverified Apache-2.0 (permissive) · 50f2b672b1461e67 · report
llama_pack3 model/llama.py unverified Apache-2.0 (permissive) · ac39ef2ac4b2aa39 · report
mistral_pack3 model/mistral.py unverified Apache-2.0 (permissive) · be9ddf29d82d32eb · report
opt_pack3 model/opt.py unverified Apache-2.0 (permissive) · 5a1ab8a11275fe3d · 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. 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.

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

generated Assembly for ShiftAddLLM (graph method: ShiftAddLLM), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 5 property tests passed on both).

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

  1. least_squares_solve_scales entry · level 3 · ran · violated contract · 8de7e805f8c50887c7341d1cbea430e87af567ef21e1b43641dab8b2e2c94dc1

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="2406.05981") returns these assemblies with each brick's role and wiring (how to connect).

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