Papers › AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment

AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment

15 Nov 2024arXiv:2411.10606archive 2025-07-28

Yonggan Fu, Zhongzhi Yu, Junwei Li, Jiayi Qian, Yongan Zhang, Xiangchi Yuan, Dachuan Shi, Roman Yakunin, Yingyan Celine Lin

Motivated by the transformative capabilities of large language models (LLMs) across various natural language tasks, there has been a growing demand to deploy these models effectively across diverse real-world applications and platforms. However, the challenge of efficiently deploying LLMs has become increasingly pronounced due to the varying application-specific performance requirements and the rapid evolution of computational platforms, which feature diverse resource constraints and deployment flows. These varying requirements necessitate LLMs that can adapt their structures (depth and width) for optimal efficiency across different platforms and application specifications. To address this critical gap, we propose AmoebaLLM, a novel framework designed to enable the instant derivation of LLM subnets of arbitrary shapes, which achieve the accuracy-efficiency frontier and can be extracted immediately after a one-time fine-tuning. In this way, AmoebaLLM significantly facilitates rapid deployment tailored to various platforms and applications. Specifically, AmoebaLLM integrates three innovative components: (1) a knowledge-preserving subnet selection strategy that features a dynamic-programming approach for depth shrinking and an importance-driven method for width shrinking; (2) a shape-aware mixture of LoRAs to mitigate gradient conflicts among subnets during fine-tuning; and (3) an in-place distillation scheme with loss-magnitude balancing as the fine-tuning objective. Extensive experiments validate that AmoebaLLM not only sets new standards in LLM adaptability but also successfully delivers subnets that achieve state-of-the-art trade-offs between accuracy and efficiency.

PaperPDFCodeCode Syntology ran

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 13 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) · 4 unverified. Where Syntology's instrument failed: 4 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: 13 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 2026-09-25 (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/AmoebaLLM officialmentioned on GitHubjaxMITSyntology: 13 samples, 9 ran (6 instrument-failed) · 4 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: 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) · 4 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.

4ran · our draft was wrong
2ran; the contract check could not run
3ran
4unverified

Licence: 6 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. For 6 of them, 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/AmoebaLLM. “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/AmoebaLLM official repository 13 samples, 9 ran (6 instrument-failed) · 4 unverified
batch_split eval_func.py ran · our draft was wrong fingerprinted MIT (permissive) · 3bf1c3c00271897f · report fixture: signature prompts:list/1/str, batch_num:int/0/int · returned list · level recorded 2026-09-25
compute_metrics in 208 papers eval_func.py ran MIT (permissive) · 89809a6f227449c9 · report fixture: signature args:NoneType/0/?, results:dict/0/?, total_num:int/0/int · returned float · level recorded 2026-09-25
get_config_class_from_processor_class in 29 papers transformers/utils/create_dummy_models.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only · 3d999b95009c7537 · report fixture: signature processor_class:callable/0/? · returned type · level recorded 2026-09-25
get_processor_types_from_config_class in 29 papers transformers/utils/create_dummy_models.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only · 0c0b81b081919d8e · report fixture: signature config_class:callable/0/?, allowed_mappings:list/1/str · returned tuple · level recorded 2026-09-25
get_wikitext2 in 78 papers width_shrink/data.py ran MIT (permissive) here; the stored copy is pointer only · dee8be97b2cf4692 · report fixture: returned tuple · level recorded 2026-09-22
hash_args in 46 papers lm-evaluation-harness/lm_eval/api/model.py ran · our draft was wrong fingerprinted MIT (permissive) · 20a7cc804eb22661 · report fixture: signature attr:str/0/str, args:tuple/1/str · returned str · level recorded, date not recorded
parse_eval_args in 16 papers lm-evaluation-harness/lm_eval/__main__.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 400ea4f64ccce5ef · report fixture: signature parser:ArgumentParser/0/? · returned Namespace · level recorded 2026-09-22
prepare_input in 17 papers eval_func.py ran MIT (permissive) · 5dc37098fd3e0e07 · report fixture: signature tokenizer:MockTokenizer/0/?, prompts:list/1/str · returned dict · level recorded 2026-09-25
request_caching_arg_to_dict in 18 papers lm-evaluation-harness/lm_eval/evaluator.py ran · our draft was wrong fingerprinted MIT (permissive) · c44830a7722ff5f7 · report fixture: signature cache_requests:str/0/str · returned dict · level recorded, date not recorded
get_architectures_from_config_class in 29 papers transformers/utils/create_dummy_models.py unverified MIT (permissive) here; the stored copy is pointer only · b176efb26f72e507 · report
get_c4 in 41 papers width_shrink/data.py unverified MIT (permissive) here; the stored copy is pointer only · 7630a157a3b32ab9 · report
get_loaders in 51 papers width_shrink/data.py unverified MIT (permissive) · 16994008353af958 · report
prepare_calibration_input in 17 papers width_shrink/prune.py unverified MIT (permissive) · a5c450766875733e · report

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