Piris Labs: Inference at Light Speed
We deliver low-latency, low-cost AI inference by eliminating the memory wall using full-stack optical interconnects and a purpose-built software stack.
Details
- External ID
- 97751
- Source
- YC
- Company
- Piris Labs
- Product
- Piris Labs: We Set the Fastest Reported GLM-5.2 Inference Speed
- Website domain
- pirislabs.io
- Launched
- Feb. 12, 2026
- Cohort
- Winter 2026
- Upvotes
- 21
- Upvotes percentile
- 0.49612403100775193
- Tags
- Artificial Intelligence, Hard Tech, Hardware, Infrastructure
- Fetched at
- Oct. 1, 2026, 1 a.m.
- Updated at
- Oct. 1, 2026, 1 a.m.
Enrichment
- Theme
- ML inference and model optimization
- Vertical
- Horizontal
- Function
- Model & infra
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Commercial product
- Normalized one-liner
- low-latency ai inference using optical interconnects
- Manually corrected
- False
Could you build this?
No Eliminating memory bottlenecks using custom optical interconnects and vertically integrated hardware/software inference stacks requires world-class photonics, hardware engineering, and low-level systems programming.
What it would actually take: This venture involves physical optical transceiver and silicon photonics hardware design, board layout, and hardware fabrication. On the software side, it requires writing custom low-level device drivers, custom CUDA/Triton kernels, and optical network fabrics (MPI/NCCL alternatives) for distributed LLM inference. Doing this requires multi-disciplinary teams of optical engineers, chip architects, and systems/kernel developers with millions in capital expenditures.
Competitors
Other products that read as similar to this one — 278 launches clear the similarity bar, closest 8 shown.
Attention rank: #121 of 279 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 100 days after the earliest competitor.
- Dipole Labs: Shooting lasers to solve the billion-dollar bottleneck inside AI datacenters · yc · 2026-08-13 · 9 upvotes · similarity 0.54
- OpenRelay: The Inference Delivery Network · yc · 2026-08-07 · 11 upvotes · similarity 0.53
- Lamb Labs: Custom Chips for AI Inference · yc · 2026-08-03 · 64 upvotes · similarity 0.51
- Orchestra: Self-optimizing inference cloud to cut your AI costs by 100x · yc · 2026-09-07 · 5 upvotes · similarity 0.49
- Dreamscale Labs: Running robot brains in the cloud · yc · 2026-09-17 · 50 upvotes · similarity 0.49
- Reame · hn · 2026-07-11 · 59 upvotes · similarity 0.47
- General Compute · ph · 2026-05-22 · 314 upvotes · similarity 0.46
- zlaya · github · 2026-09-23 · 9 upvotes · similarity 0.46
Other launches for this product
Same idea, different domain
Nobody's really built a model & infra tool for Fintech yet.