Platform for deploying and routing GPU-accelerated inference, streaming, and batch workloads at scale.
-
Updated
Sep 9, 2026 - Go
#
serverless-gpu
Here are 25 public repositories matching this topic...
Run AI models anywhere. https://muna.ai/explore
-
Updated
Sep 3, 2026 - Python
Run ComfyUI on Modal with auto-scaling, GPU snapshots, and easy model management. Try image, video generation via ComfyUI on Modal.
image-generation gpu-computing video-generation cloud-gpu serverless-gpu comfyui wan-2-2 modal-gpu minimax-h3
-
Updated
Sep 6, 2026 - Python
Own your AI video pipeline. LTX-2.3 (22B) self-hosted on your Modal GPU via a Claude Code skill — t2v, i2v, keyframes, v2v + synced audio. ~$0.02 per 5s clip, idle = $0.
modal self-hosted video-generation image-to-video diffusion-models text-to-video serverless-gpu ai-video agent-skills ltx-video claude-skills claude-code-skill
-
Updated
Jun 11, 2026 - Python
Single-user training and generation platform on Modal. Train Krea 2 LoRAs, generate stills, and turn them into video with MiniMax-H3 (sound and picture in one pass) — one deploy, one URL, no infrastructure to keep alive.
modal lora text-to-image diffusion image-to-video text-to-video serverless-gpu comfyui krea2 minimax-h3
-
Updated
Sep 9, 2026 - Python
State-aware hedged requests for serverless GPU inference — return the first valid result and cancel the losers with an audited receipt.
python modal inference cold-start speculative-execution mlops serverless-gpu runpod hedged-requests cerebrium
-
Updated
Jul 16, 2026 - Python
AI-powered audio transcription, voice cloning, and image generation on Modal serverless GPUs. Real-time streaming, speaker diarization, meeting minutes, saved voice profiles, and FLUX.1 image gen — all in one service.
python flux text-to-speech streaming modal image-generation speech-to-text transcription nemo speaker-diarization voice-cloning fastapi serverless-gpu qwen-tts nvidia-parakeet
-
Updated
Apr 16, 2026 - Python
Queue-driven, scale-from-zero GPU inference for any Kubernetes — bursts to cross-region VMs when GPUs run dry
python kubernetes machine-learning gpu helm inference self-hosted gpu-computing autoscaling inference-server model-serving ml-infrastructure mlops scale-to-zero serverless-gpu batch-inference serverless-inference gpu-inference ai-infrastructure
-
Updated
Jun 20, 2026 - Python
An open-source, BYOK YouTube thumbnail and channel analyzer powered by the TRIBE v2 neuroscience model, Next.js, and serverless GPU inference via Modal.
react python open-source machine-learning youtube ai computer-vision nextjs neuroscience self-hosted developer-tools youtube-analytics bring-your-own-key serverless-gpu supabase ai-inference creator-economy byok modal-labs neuromarketing
-
Updated
Jun 2, 2026 - JavaScript
🔎 Search your photos by meaning — semantic photo search powered by CLIP on Runpod Flash serverless GPUs
-
Updated
Jun 30, 2026 - Python
Run Metaflow steps on serverless GPUs — no infrastructure to manage
python machine-learning gpu pypi modal distributed-computing mlops serverless-gpu metaflow metaflow-plugin
-
Updated
Mar 9, 2026 - Python
A post-AGI framework using serverless agents to optimize Earth's carrying capacity by guiding natural evolution and implementing AI nap protocols.
sustainability evolution agi human-in-the-loop green-computing serverless-gpu apache-2-0 bio-orchestration
-
Updated
Jan 24, 2026
High-Performance Serverless event and data processing platform
-
Updated
Dec 21, 2019 - Go
One-command PowerShell deployment of Ollama running gpt-oss:20b (or any Ollama model) on Azure Container Apps serverless GPU — nginx API-key auth proxy, scale-to-zero billing.
nginx powershell azure gpu iac api-key serverless-gpu azure-container-apps llm ollama self-hosted-llm gpt-oss
-
Updated
Jul 4, 2026 - PowerShell
AI-powered genetic variant analysis platform using Stanford's Evo 2 model to predict mutation pathogenicity. Built with Next.js, FastAPI, and Serverless GPU acceleration for real-time genomic research and clinical decision support.
-
Updated
May 23, 2025 - TypeScript
A cost-effective, serverless AI image generation pipeline using local n8n and Modal.com to run the uncensored FLUX.2-klein-9B model on cloud A100 GPUs.
flux automation modal n8n serverless-gpu stable-diffusion ai-image-generation uncensored-ai flux-2-dev
-
Updated
May 18, 2026 - Python
LTX-2 video generation packaged for RunPod serverless GPU workers.
-
Updated
Jan 15, 2026 - Python
Serverless GPU cold start latency and cost benchmark for LLM inference (Modal, RunPod, Replicate, Together AI).
-
Updated
Sep 3, 2026
AI-powered medical imaging platform for DICOM ingestion, MONAI multi-organ segmentation, and MPR visualization with PHI de-identification, real-time inference streaming, and clinical PDF reporting.
react python typescript computer-vision websocket dicom pytorch medical-imaging segmentation radiology tailwindcss vite fastapi clinical-informatics serverless-gpu healthcare-ai monai open-source-healthcare phi-deidentification vitedeep-learning
-
Updated
Sep 4, 2026 - Python
Moving one app's image generation onto Runpod serverless and measuring it honestly: 388.63s to 325.24s end to end, $1.13 total spend, 0 differing pixels against the home render. Every number cites a log that a script checks.
python docker benchmark serverless gpu-computing lora reproducibility cost-analysis serverless-gpu runpod stable-diffusion comfyui sdxl ip-adapter
-
Updated
Aug 19, 2026 - Python
Add this topic to your repo
To associate your repository with the serverless-gpu topic, visit your repo's landing page and select "manage topics."