Viewing profile — medicis123

We did something similar - Streaming experts. Maintaining an expert cache, optimizing it to simulate running a multi-model agentic workflow on a 2-DGC Spark Cluster. The models we …

Hi All, We are so excited to share the numbers and benchmark reports on our new inference server built specifically to run multi-model agentic workflows on DGX Spark clusters. We r…

We have built a GPU Runtime for Nvidia GPUs that can run multiple development/experimental/inference workloads per GPU with safe overcommit of VRAM, dynamic fractional allocation o…

Most GPU “sharing” solutions today (MIG, time-slicing, vGPU, etc.) still behave like partitions: you split the GPU or rotate workloads. That helps a bit, but it still leaves huge p…

WoolyAI disaggregates GPU compute from CPU and routes GPU operations from ML jobs running on CPU-only infra into a shared heterogeneous GPU pool(Nvidia+AMD), where a GPU hypervisor…

We have opened the WoolyAI GPU hypervisor trial to all. https://woolyai.com/signup/ - Higher GPU utilization & lower cost Pack many jobs per GPU with WoolyAI’s server-side schedule…

Hi, I wanted to share some information on this cool feature we built in WoolyAI GPU hypervisor, which enables users to run their existing Nvidia CUDA pytorch/vLLM projects and pipe…

We built this feature in our GPU Hypervisor, which cleanly separates your user-space ML environment from the GPU runtime, so you can code locally, run remotely, and execute kernels…

We have just published a short demo of the WoolyAI GPU Hypervisor, showcasing VRAM memory sharing/deduplication. Load a single base model once, then run multiple isolated LoRA stac…

Looks interesting. Will give it a try. I have been following AI startups developing various agents(Agentic phenomenon). Are you using OPenAi and any other LLM service APIs or you f…

We ran it on WoolyAI Acceleration Service https://docs.woolyai.com/getting-started/running-your-first-... There are some interesting insights just looking at these numbers. Environ…

Hi HN, We’re a small team of OS, virtualization, and ML engineers, and after three years of development, we’re thrilled to launch the beta of our CUDA abstraction layer! We decoupl…

Wanted to share that we developed a GitLab CI Runner/executor for Anka Build and have made it public (It was done for one of our user). It basically enables you to run your iOS/mac…