Field note
What it does
Cloud platform providing dynamic batching, containerized inference, and GPU-accelerated model serving with caching and auto-scaling.
Capabilities
Available capabilities
Asynchronous Job ProcessingWeb FunctionsGenerative AI model servingBatched message processingAsynchronous dataset mappingWeb ServingPersistent VolumesSandboxed ExecutionGPU InferencePersistent Volume StorageContainer Lifecycle HooksCustom container imagesServerless DeploymentDistributed ComputingContainer EnvironmentsCUDA GPU SupportLLM ServingGPU ComputeServerless GPU executionGPU ComputingServerless functionsAPI SandboxSecrets ManagementJob queuesVolume-based model cachingOpenAI-compatible APIFine-tuningDynamic batchingAutoscalingGPU-accelerated Functions
Tags
Tags
Ways to use it
Ways to use it
sdk
python / modal
other
python / transformers
sdk
python / modal
sdk
python / diffusers
sdk
python / accelerate
sdk
python / wandb
openapi
Not filed / Not filed
other
python / Not filed
sdk
python / modal
sdk
python / openai
other
python / vllm
other
python / locust