Home › Code › cleanup_memory

cleanup_memory

Syntologyentry name in harvested coderead from the graph 2026-09-24

cleanup_memory appears in the code Syntology harvested for 8 papers, as 6 distinct code bodies found in 8 places (a place is one code body under one paper). At least one of them ran in 0 of the papers; 0 of the code bodies carry a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named cleanup_memory do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 0 of the 6 distinct code bodies named cleanup_memory; 6 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
0ran · our draft was wrong
0ran · fixture could not drive it
0ran
6unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 3 of the 8 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “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, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

8 papers shown of 8, newest first; 8 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 5 papers added by Syntology. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's 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.

PaperDateFileStatus SyntologyLicence
Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs added by Syntology 2026-05 (from id) chenxinrui-tsinghua/LinearPatch/rotate_utils/utils.py 88c8d591b4688832 unverified MIT (permissive)
Rethinking Residual Errors in Compensation-based LLM Quantization added by Syntology 2026-04 (from id) list0830/ResComp/fake_quant/utils.py 88c8d591b4688832 unverified no licence file found · pointer only
RAIN-Merging: A Gradient-Free Method to Enhance Instruction Following in Large Reasoning Models with Preserved Thinking Format added by Syntology 2026-02 (from id) K1nght/RAIN-Merging/nullspace_merge_qkvo_ffn.py 0e35eabd03de87a8 unverified MIT (permissive)
D 2 Quant: Accurate Low-bit Post-Training Weight Quantization for LLMs added by Syntology 2026-02 (from id) XIANGLONGYAN/D2Quant/d2quant/config.py 58973fc4e2b31774 unverified Apache-2.0 (permissive)
PT$^2$-LLM: Post-Training Ternarization for Large Language Models added by Syntology 2025-10 (from id) XIANGLONGYAN/PT2-LLM/pt2_llm/model_utils.py a8119d4e31042017 unverified Apache-2.0 (permissive)
Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning 20 May 2025 jiwonsong-dev/reasoningpathcompression/benchmark/throughput.py fae5b507fb9dfa12 unverified MIT (permissive)
GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibration 3 Apr 2025 intelligent-computing-lab-yale/gptaq/fake_quant/gptaq_utils.py 88c8d591b4688832 unverified no licence file found · pointer only
Attention-aware Post-training Quantization without Backpropagation 19 Jun 2024 SamsungLabs/BoA/quantizers/boa.py b9b9db4928482dd1 unverified licence not identified · pointer only

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the 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 cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

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