Papers › Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models

Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models

19 Feb 2025arXiv:2502.13533archive 2025-07-28

Jun Zhang, Jue Wang, Huan Li, Lidan Shou, Ke Chen, Yang You, Guiming Xie, Xuejian Gong, Kunlong Zhou

Large Language Models (LLMs) have significantly advanced natural language processing with exceptional task generalization capabilities. Low-Rank Adaption (LoRA) offers a cost-effective fine-tuning solution, freezing the original model parameters and training only lightweight, low-rank adapter matrices. However, the memory footprint of LoRA is largely dominated by the original model parameters. To mitigate this, we propose LoRAM, a memory-efficient LoRA training scheme founded on the intuition that many neurons in over-parameterized LLMs have low training utility but are essential for inference. LoRAM presents a unique twist: it trains on a pruned (small) model to obtain pruned low-rank matrices, which are then recovered and utilized with the original (large) model for inference. Additionally, minimal-cost continual pre-training, performed by the model publishers in advance, aligns the knowledge discrepancy between pruned and original models. Our extensive experiments demonstrate the efficacy of LoRAM across various pruning strategies and downstream tasks. For a model with 70 billion parameters, LoRAM enables training on a GPU with only 20G HBM, replacing an A100-80G GPU for LoRA training and 15 GPUs for full fine-tuning. Specifically, QLoRAM implemented by structured pruning combined with 4-bit quantization, for LLaMA-3.1-70B (LLaMA-2-70B), reduces the parameter storage cost that dominates the memory usage in low-rank matrix training by 15.81× (16.95×), while achieving dominant performance gains over both the original LLaMA-3.1-70B (LLaMA-2-70B) and LoRA-trained LLaMA-3.1-8B (LLaMA-2-13B).

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 LORAM, generated from the paper text (not the authors' code), at level 2 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)” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='LORAM') (how to connect); the free check have('2502.13533') needs no token.

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

Code

Syntology 13 code samples: 12 from 1 repository linked to this paper, 1 identical to code harvested from another paper's repository. Across all 13: 5 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 4 ran (4 with no instrument failure; 0 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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.

junzhang-zj/LoRAM officialmentioned on GitHubpytorchSyntology: 12 samples, 4 ran (0 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

13 samples harvested: 5 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 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 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.

1ran · our draft was wrong
4ran
8unverified

Licence: 1 of the 13 samples is 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 junzhang-zj/LoRAM. 1 sample is listed last, in a group without a repository. “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”. For 3 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

junzhang-zj/LoRAM official repository 12 samples, 4 ran (0 instrument-failed) · 8 unverified
LlamaMLP in 13 papers loram/2_pruned_low_rank_matrix_training.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · f96dedc8894ebbab · report fixture: returned LlamaMLP · level recorded 2026-09-22
LlamaPreTrainedModel loram/2_pruned_low_rank_matrix_training.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 1ecb31573990e76e · report fixture: returned LlamaPreTrainedModel · level recorded 2026-09-22
LlamaRMSNorm in 9 papers loram/2_pruned_low_rank_matrix_training.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 9f7bd959c5fde990 · report fixture: returned LlamaRMSNorm · level recorded 2026-09-22
LlamaRotaryEmbedding in 13 papers loram/2_pruned_low_rank_matrix_training.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · c9f2757f0827b802 · report fixture: returned LlamaRotaryEmbedding · level recorded 2026-09-22
LlamaAttention in 15 papers loram/2_pruned_low_rank_matrix_training.py unverified Apache-2.0 (permissive) · 9dee9df76b1fdd21 · report
LlamaDecoderLayer in 11 papers loram/2_pruned_low_rank_matrix_training.py unverified Apache-2.0 (permissive) · d4a037311f926e1a · report
LlamaFlashAttention2 loram/2_pruned_low_rank_matrix_training.py unverified Apache-2.0 (permissive) · f2e37ec2f6d5b640 · report
LlamaForCausalLM loram/2_pruned_low_rank_matrix_training.py unverified Apache-2.0 (permissive) · 23f836d2c7d15352 · report
LlamaModel in 9 papers loram/2_pruned_low_rank_matrix_training.py unverified Apache-2.0 (permissive) · 85f06bba96f8ecb0 · report
LlamaSdpaAttention loram/2_pruned_low_rank_matrix_training.py unverified Apache-2.0 (permissive) · 275b5715a473b63a · report
main in 235 papers loram/2_pruned_low_rank_matrix_training.py unverified Apache-2.0 (permissive) · 1382890bcd6d3bc9 · report
print_trainable_parameters in 9 papers loram/2_pruned_low_rank_matrix_training.py unverified Apache-2.0 (permissive) · 55ec6efd6c53c278 · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
apply_rotary_pos_emb in 393 papers
census: 14 implementations from 15 papers, 8 distinct outputs across 7 buckets, one shared input per bucket
repository not located ran · our draft was wrong licence of this copy not recorded · 583539efd6fd01fb · report fixture: signature q:Tensor/4/float, k:Tensor/4/float, cos:Tensor/3/float, sin:Tensor/3/float, position_ids:NoneType/0/?, unsqueeze_dim:int/0/int · returned tuple · level recorded 2026-09-22

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 LORAM (graph method: LORAM), 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, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 2).

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

  1. apply_pruning_mask entry · level 2 · ran · eedebd33bb308b027e6ed40947ba09eed067cf93d839c5f8c1c859c51d74da8f

harvested Assembly for LORAM (graph method: LORAM). 15 bricks; individually on a fixture: 7 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.

  1. main entry · level 0 · unverified · 1382890bcd6d3bc9
  2. LlamaForCausalLM helper · level 0 · unverified · 23f836d2c7d15352
  3. print_trainable_parameters helper · level 0 · unverified · 55ec6efd6c53c278
  4. LlamaModel helper · level 0 · unverified · 85f06bba96f8ecb0
  5. LlamaPreTrainedModel helper · level 1 · ran · 1ecb31573990e76e
  6. LlamaDecoderLayer helper · level 0 · unverified · d4a037311f926e1a
  7. LlamaRMSNorm helper · level 1 · ran · 9f7bd959c5fde990
  8. LlamaRotaryEmbedding helper · level 1 · ran · c9f2757f0827b802
  9. LlamaMLP helper · level 1 · ran · f96dedc8894ebbab
  10. LlamaAttention helper · level 0 · unverified · 9dee9df76b1fdd21
  11. LlamaFlashAttention2 helper · level 0 · unverified · f2e37ec2f6d5b640
  12. LlamaSdpaAttention helper · level 0 · unverified · 275b5715a473b63a
  13. apply_rotary_pos_emb helper · level 1 · ran · our draft was wrong · 583539efd6fd01fb
  14. repeat_kv helper · level 2 · ran; the contract check could not run · 3c76e52815c5401d
  15. rotate_half helper · level 1 · ran · our draft was wrong · e03d53ba9d4f9ae5

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="2502.13533") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Quantization

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

AdapterPruning

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