MétaCan
Menu
Back to cohort
Record W7115041457

HarMoEny: Efficient multi-GPU inference of Mixture of Experts models by scheduling experts across accelerators

2025· dissertation· en· W7115041457 on OpenAlexaff

Bibliographic record

VenueeScholarship@McGill (McGill) · 2025
Typedissertation
Languageen
FieldComputer Science
TopicMobile Crowdsensing and Crowdsourcing
Canadian institutionsMcGill University
Fundersnot available
KeywordsInferenceScheduling (production processes)Mixture modelJob shop schedulingExpert system
DOInot available

Abstract

fetched live from OpenAlex

Mixture-of-Experts (MoE) models enhance computational efficiency during inference by selectively activating specialized experts for each request.This approach facilitates efficient model scaling on multi-GPU systems leveraging expert parallelism, without compromising performance.However, uneven load distribution across experts often creates imbalances across GPUs, increasing latency due to idle waiting times.To address this, we propose HarMoEny, a novel solution that employs two simple techniques: (i) dynamic token redistribution to underutilized GPUs and (ii) asynchronous prefetching of experts from system to GPU memory.These methods achieve near-perfect load balancing across GPUs and amortize the cost of executing experts not resident in GPU memory, thereby reducing waiting times and latency.We implement HarMoEny and evaluate its performance against four state-of-the-art baselines using real-world and artificially imbalanced datasets.Under heavy load imbalance, HarMoEny improves throughput by 66.7%-68.6%and reduces time to first token by 31.8%-37.2%,compared to the next-best baseline.Furthermore, our ablation study demonstrates that HarMoEny's scheduling policy reduces the GPU idle time by up to 99% relative to the baseline policies.i AbrgLes modles Mixture-of-Experts (MoE) amliorent l'efficacit computationnelle lors de l'infrence en activant slectivement des experts spcialiss pour chaque requte.Cette approche permet une monte en chelle efficace des modles sur des systmes multi-GPU grce au paralllisme d'experts, sans compromettre les performances.Cependant, une rpartition ingale de la charge entre les experts engendre souvent des dsquilibres entre les GPU, augmentant ainsi la latence cause des temps d'attente inactifs.Pour remdier cela, nous proposons HarMoEny, une solution novatrice qui repose sur deux techniques simples : (i) la redistribution dynamique des jetons vers les GPU sous-utiliss et (ii) le prchargement asynchrone des experts de la mmoire systme vers la mmoire GPU.Ces mthodes permettent un quilibrage de charge quasi-parfait entre les GPU et amortissent le cot d'excution des experts non prsents en mmoire GPU, rduisant ainsi les temps d'attente et la latence.Nous avons implment HarMoEny et valu ses performances face quatre rfrences de pointe, en utilisant des jeux de donnes rels et artificiellement dsquilibrs.En cas de fort dsquilibre de charge, HarMoEny amliore le dbit de 66,7 % 68,6 % et rduit le temps jusqu'au premier jeton de 31,8 % 37,2 %, par rapport la meilleure rfrence.De plus, notre tude d'ablation montre que la politique d'ordonnancement de HarMoEny rduit le temps d'inactivit des GPU jusqu' 99 % par rapport aux politiques de rfrence.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: Bench or experimental
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.226
Threshold uncertainty score0.999

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0020.001
Bibliometrics0.0010.001
Science and technology studies0.0010.000
Scholarly communication0.0000.001
Open science0.0030.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.027
GPT teacher head0.280
Teacher spread0.253 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designBench or experimental
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueeScholarship@McGill (McGill)Same topicMobile Crowdsensing and CrowdsourcingFrench-language works237,207