Curated FOSS Directory for Community and Discussion

Back openlake-project/openlake

openlake

openlake

OpenLake is a high performance storage engine for efficient LLM inference and GPU Training

2.5k 42422 HN points

last commit 2026-07-26

blackwell gpt gpu high-performance llm llm-training model-serving rdma rust storage

Share:

About

OpenLake is a high performance storage engine for efficient LLM inference and GPU Training

Languages

Rust76.1%TypeScript7.3%CSS5.8%Cuda4.2%JavaScript3.5%C1.4%Shell0.7%Dockerfile0.3%Go Template0.3%CMake0.2%Python0%

Contributors22

ArnavBalyan

vatantomar007

9

Prabhjeet8963

4

nidhii170706

4

0xnktd

2

HARSHKUMAR786142

2

VivaanHooda

2

ayushrichh

2

dakshdahiya633-tech

2

parvagrawal08

2

Aayush-54

1

Abhimanyu7920

1

Mayank-Rawat-1708

1

mehulbansal517

1+8

No features listed.

Comments Theme

Install

Cargo

Keywords

high-performance

slug: openlake

On Hacker News

Show HN: Cuts Long Horizon Inference Costs by 50% via external KV Cache Offload

Read the discussion

Sponsored

300 × 250 (IAB)

Sponsor

Sponsor

Sponsor

Sponsor

300 × 250 (IAB)

300 × 250 (IAB)

Sponsored

300 × 250 (IAB)

Sponsor

Sponsor

Sponsor

Sponsor

300 × 250 (IAB)

300 × 250 (IAB)