Hacker News new | ask | show | jobs
user: medicis123
created: 2018-07-11
karma: 4

submissions:

Show HN: Stop GPU pods placement getting bottlenecked by reserved VRAM
2 points | 0 comments
A New Approach to GPU Sharing: Deterministic, SLA-Based GPU Kernel Scheduling
1 points | 0 comments
Show HN: Disaggregating GPU compute from CPU in ML job execution to scale GPUs
1 points | 0 comments
Show HN: Run PyTorch on CPU boxes, offload kernels to remote GPUs
1 points | 0 comments
Running Nvidia CUDA PyTorch container project/pipelines on AMD with no changes
1 points | 0 comments
0 points | 0 comments
GPU-accelerated code on CPU-only environments -Remote GPU Kernel Execution
1 points | 1 comments
0 points | 0 comments
Sharing base model in GPU VRAM across multiple inference stack process [video]
7 points | 1 comments
0 points | 0 comments
0 points | 0 comments
Sharing actual GPU core and VRAM utilization metrics for query on 10 LLM models
1 points | 1 comments
Show HN: WoolyAI-CUDA Abstraction Layer to Decouple Kernel Shader Exec on GPU
4 points | 0 comments
Locally delivered and centrally managed macOS envs for privileged access setup
1 points | 0 comments
0 points | 0 comments
Shopify scaling iOS CI with Anka
1 points | 0 comments