Corsair
Click to visit website
About
d-Matrix has developed Corsair, an AI inference platform for datacenters. Corsair boasts impressive performance, achieving 60,000 tokens/sec at 1ms/token latency for Llama3 8B and 30,000 tokens/sec at 2ms/token latency for Llama3 70B, all within a single server or rack, respectively. The platform is designed for speed, efficiency, sustainability, and scalability, addressing the growing need for performant and cost-effective Generative AI solutions. d-Matrix is backed by significant funding and comprises a team of experienced industry veterans. The company's focus is on making large-scale AI inference commercially viable and sustainable. They offer various job opportunities across several locations.
Platform
Task
Features
• energy efficient
• scales with model size
• 30,000 tokens/sec at 2ms/token latency for llama3 70b in a single rack
• 60,000 tokens/sec at 1ms/token latency for llama3 8b in a single server
• ultra low latency without compromising throughput
Job Opportunities
Technical Recruiter, Senior Staff G&A Recruiting
Corsair is a high-performance, energy-efficient AI inference platform designed for datacenters, offering blazing fast speeds and commercial viability.
Benefits:
Competitive pay and equity
Health care
Flexible time-off
Paid paternity leave
401k retirement plan
Show more details
Machine Learning Computer Architect, Staff - Workload Analysis
Corsair is a high-performance, energy-efficient AI inference platform designed for datacenters, offering blazing fast speeds and commercial viability.
Benefits:
Competitive pay and equity
Health care
Flexible time-off
Paid paternity leave
401k retirement plan
Show more details
AI Security Architect, Senior Staff
Corsair is a high-performance, energy-efficient AI inference platform designed for datacenters, offering blazing fast speeds and commercial viability.
Benefits:
Competitive pay and equity
Health care
Flexible time-off
Paid paternity leave
401k retirement plan
Show more details
Ratings & Reviews
No ratings available yet. Be the first to rate this tool!
Alternatives
Modular MAX
Modular's MAX is a free, open-source AI inference framework, complemented by the high-performance Mojo programming language. Enterprise support is also available.
View Details
MK1
MK1 provides a suite of AI tools focused on high-performance LLM inference, long-context processing, and cost reduction.
View Details
ZETIC.ai
ZETIC.ai is a platform for building zero-cost, on-device AI, enabling server-less AI inference and freeing users from reliance on GPU clouds.
View Details
Inferenceable
Open-source AI inference server written in Node.js, utilizing llama.cpp and parts of llamafile C/C++ core.
View Details
Blumind
Blumind offers all-analog AI solutions for low-power, low-latency edge computing, targeting applications like voice UI, sensor analysis, and visual trigger detection across diverse industries.
View DetailsFeatured Tools
GirlfriendGPT
NSFW AI chat platform with customizable characters, AI image generation, and voice chat. Explore roleplay and intimate interactions with AI companions.
View Details
Animate My Pic
Animate My Pic is an AI photo to video tool that leverages advanced AI to effortlessly animate your pictures, offering image-to-video, text-to-video, and 30+ effects.
View Details
Nano Banana AI
Nano Banana AI is a powerful AI image editor for quick, precise editing, adjustments, and optimization of images, leveraging advanced image-to-image AI models.
View Details
Nano Banana
Nano Banana is Google's state-of-the-art AI image generator powered by Gemini 2.5 Flash Image, offering character consistency and natural language image transformation.
View Details
alivemoment
alivemoment is an AI tool that transforms cherished photos into living stories, allowing users to relive precious moments with gentle, lifelike motion.
View Details
Make Song
Make Song is an AI music and song generator that creates 100% royalty-free songs from text or lyrics in seconds, perfect for any commercial use.
View Details