Papers › Automatic heterogeneous quantization of deep neural networks for low-latency inference...
Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors
Claudionor N. Coelho Jr., Aki Kuusela, Shan Li, Hao Zhuang, Thea Aarrestad, Vladimir Loncar, Jennifer Ngadiuba, Maurizio Pierini, Adrian Alan Pol, Sioni Summers
Although the quest for more accurate solutions is pushing deep learning research towards larger and more complex algorithms, edge devices demand efficient inference and therefore reduction in model size, latency and energy consumption. One technique to limit model size is quantization, which implies using fewer bits to represent weights and biases. Such an approach usually results in a decline in performance. Here, we introduce a method for designing optimally heterogeneously quantized versions of deep neural network models for minimum-energy, high-accuracy, nanosecond inference and fully automated deployment on chip. With a per-layer, per-parameter type automatic quantization procedure, sampling from a wide range of quantizers, model energy consumption and size are minimized while high accuracy is maintained. This is crucial for the event selection procedure in proton-proton collisions at the CERN Large Hadron Collider, where resources are strictly limited and a latency of 𝒪(1) μs is required. Nanosecond inference and a resource consumption reduced by a factor of 50 when implemented on field-programmable gate array hardware are achieved.
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):
get_harvested_code_for_paper(arxiv_id="2006.10159")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2006.10159", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2006.10159")
Code
The archive's official repository (google/qkeras) was not harvested; the 26 samples below come from 2 community repositories.
Syntology 26 code samples harvested from 2 repositories linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 12 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.
By repository: community (archive-listed): 26 samples from 2 repositories, 14 ran (14 with no instrument failure; 0 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
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
26 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 12 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.
Licence: 0 of the 26 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.
c7c761fbe641c432 · report
fixture: signature x:EagerTensor/2/float · returned SymbolicTensor · level recorded 2026-09-24 79068918a6559176 · report
fixture: signature x:EagerTensor/2/float · returned SymbolicTensor · level recorded 2026-09-24 2230bec278fc10ac · report
fixture: signature x:EagerTensor/2/float · returned SymbolicTensor · level recorded 2026-09-24 1431e3fdf61bc841 · report
fixture: signature func:callable/0/?, k:int/0/int, i:int/0/int, f:int/0/int · returned tuple · level recorded 2026-09-24 2b7074bd7febc4ce · report
fixture: signature arr:ndarray/2/float, silent:bool/0/bool · returned tuple · level recorded 2026-09-24 1643f065017821aa · report
fixture: signature x:EagerTensor/2/float, scale:EagerTensor/0/float · returned EagerTensor · level recorded 2026-09-24 83b44746819d42d2 · report
9094378ccf4b5d24 · report
c5da803484bb9815 · report
fixture: signature x:ndarray/3/float, classes:int/0/int, value_range:int/0/int, with_residue:bool/0/bool, merge_with_channels:bool/0/bool, use_two_hot_encoding:bool/0/bool · returned ndarray · level recorded 2026-09-24 09398a22daae3b96 · report
fixture: signature activation:str/0/str · returned str · level recorded 2026-09-24 4a20b411848af1c8 · report
fixture: signature filters:int/0/int, kernel_size:int/0/int, alpha:float/0/float, strides:tuple/1/int, padding:str/0/str, kernel_initializer:str/0/str, bias_initializer:str/0/str, kernel_regularizer:NoneType/0/?, bias_regularizer:NoneType/0/?, kernel_constraint:NoneType/0/?, bias_constraint:NoneType/0/?, activation:str/0/str, use_separable:bool/0/bool, name:str/0/str, acc_quantizer:NoneType/0/? · returned function · level recorded 2026-09-24 5b480cd73cbf0ae1 · report
fixture: signature pool_size:tuple/1/int, strides:NoneType/0/?, padding:str/0/str, quantizer:MockQuantizer/0/? · returned function · level recorded 2026-09-24 51aca2e834d8e57b · report
fixture: signature filters:int/0/int, kernel_size:tuple/1/int, alpha:float/0/float, strides:tuple/1/int, padding:str/0/str, kernel_initializer:str/0/str, bias_initializer:str/0/str, kernel_regularizer:NoneType/0/?, bias_regularizer:NoneType/0/?, kernel_constraint:NoneType/0/?, bias_constraint:NoneType/0/?, use_separable:bool/0/bool, name:str/0/str, bias_quantizer:NoneType/0/?, kernel_quantizer:NoneType/0/?, depthwise_quantizer:NoneType/0/?, pointwise_quantizer:NoneType/0/?, acc_quantizer:str/0/str, pooling_quantizer:NoneType/0/?, depthwise_activation:NoneType/0/?, activation:str/0/str, bias_range:float/0/float, kernel_range:float/0/float, depthwise_range:float/0/float, pointwise_range:float/0/float · returned function · level recorded 2026-09-24 ea660d6b06041d4b · report
fixture: signature quantizer:callable/0/?, constraint:callable/0/?, initializer:callable/0/? · returned tuple · level recorded 2026-09-24 0933ca9566b5853e · report
fixture: signature identifier:dict/0/? · returned GlorotUniform · level recorded 2026-09-24 6045502d0ac2cac6 · report
fixture: signature weights:ndarray/3/float, bits:int/0/int, axis:int/0/int, quantizer:callable/0/? · returned tuple · level recorded 2026-09-24 8cb668d99317276e · report
137ccff456a7e506 · report
a82c2216301a1929 · report
4fa726dc402437bf · report
f2ab22c43ea69345 · report
65e79f2957133bfa · report
441e9baf5738fe1e · report
Tasks
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