SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.08804 · 2022

A GPU-specialized Inference Parameter Server for Large-Scale Deep Recommendation Models

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 0 failures of our instrument; 0 no recorded run), measured 2026-11-21; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2210.08804.json · badge: /api/ran/2210.08804.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
nvidia-merlin/hugectr canonical (classifier label)
classifier basis not recorded on the link
5 ran · 0 no recorded run
FunctionStatusWhere it lives
ev_size_compensation Ran
ran on a synthesized input
nvidia-merlin/hugectr/benchmarks/embedding_collection/hugectr/sharding/planner.py
pointer only (licence: Apache-2.0) · get_code("cf8edacee97b72ac")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, nvidia-merlin/hugectr, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

generate_plan_ragged_ev_size Ran
ran on a synthesized input
nvidia-merlin/hugectr/benchmarks/embedding_collection/hugectr/sharding/generate_plan.py
pointer only (licence: Apache-2.0) · get_code("389c03ce0654fff4")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, nvidia-merlin/hugectr, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_byte_per_elem Ran
ran on a synthesized input
nvidia-merlin/hugectr/benchmarks/embedding_collection/hugectr/sharding/generate_plan.py
pointer only (licence: Apache-2.0) · get_code("18c61dd6e77da138")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, nvidia-merlin/hugectr, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_tensor_names Ran
ran on a synthesized input
nvidia-merlin/hugectr/onnx_converter/hugectr2onnx/hugectr_loader.py
pointer only (licence: Apache-2.0) · get_code("aafcd554bd6ecdad")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, nvidia-merlin/hugectr, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

int_to_string Ran
ran on a synthesized input
nvidia-merlin/hugectr/benchmarks/embedding_collection/hugectr/sharding/generate_plan.py
pointer only (licence: Apache-2.0) · get_code("19835db2f190a65a")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, nvidia-merlin/hugectr, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 5 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recommendation systems are of crucial importance for a variety of modern apps and web services, such as news feeds, social networks, e-commerce, search, etc. To achieve peak prediction accuracy, modern recommendation models combine deep learning with terabyte-scale embedding tables to obtain a fine-grained representation of the underlying data. Traditional inference serving architectures require deploying the whole model to standalone servers, which is infeasible at such massive scale. In this paper, we provide insights into the intriguing and challenging inference domain of online recommendation systems. We propose the HugeCTR Hierarchical Parameter Server (HPS), an industry-leading distributed recommendation inference framework, that combines a high-performance GPU embedding cache with an hierarchical storage architecture, to realize low-latency retrieval of embeddings for online model inference tasks. Among other things, HPS features (1) a redundant hierarchical storage system, (2) a novel high-bandwidth cache to accelerate parallel embedding lookup on NVIDIA GPUs, (3) online training support and (4) light-weight APIs for easy integration into existing large-scale recommendation workflows. To demonstrate its capabilities, we conduct extensive studies using both synthetically engineered and public datasets. We show that our HPS can dramatically reduce end-to-end inference latency, achieving 5~62x speedup (depending on the batch size) over CPU baseline implementations for popular recommendation models. Through multi-GPU concurrent deployment, the HPS can also greatly increase the inference QPS.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2210.08804")
get_code_for_paper("2210.08804")
have("2210.08804")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2210.08804.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2210.08804.svg)](https://syntology.ai/paper/2210.08804)

Connect an agent — have() is free.