Modal · Resources
Resources listings from Modal on TechiSeek. 124 public listings.
- Sandbox resources and pricing (Modal)Configure CPU, memory, and other resources for Modal Sandboxes.
- Customer Supplied Encryption Keys (Modal)Use Customer Supplied Encryption Keys to protect supported Modal resources with key material that Modal does not store.
- Environments (Modal)Modal Environments isolate Modal applications and resources from one another.
- Apps, Functions, and entrypoints (Modal)An App represents an application running on Modal. It groups one or more Functions for atomic deployment and acts as a shared namespace.
- Passing local data (Modal)If you have a function that needs access to some data not present in your Python files themselves you have a few options for bundling that…
- Multi-node Clusters (Modal)Multi-node inference and training with Modal Clusters.
- GPU acceleration (Modal)Modal makes it easy to run your code on GPUs.
- Modal Functions (Modal)Modal Functions execute Python code using highly scalable serverless cloud compute.
- Networking and security (Modal)Sandboxes are built to be secure-by-default, meaning that a default Sandbox has no ability to accept incoming network connections or access…
- Sandbox Secret Injection (Modal)Sandbox Secret Injection An Outbound Policy lets a Sandbox call external HTTPS APIs that require authentication without the API key ever be…
- Invoking deployed Functions (Modal)Note that lookups are supported only for deployed Apps. Looking up a Function will fail if its App is ephemeral, e.g.
- What is a scoreboard stall? (Modal)Click this button to let us know on Git Hub. A scoreboard stall occurs when an instruction cannot be issued due to a dependency on the resu…
- What is a Warp Scheduler? (Modal)Click this button to let us know on Git Hub. The Warp Scheduler of the Streaming Multiprocessor (SM) decides which group of threads to exec…
- JavaScript SDK Reference (Modal)Complete API reference for the Modal JavaScript SDK.
- What is the CUDA Runtime API? (Modal)Click this button to let us know on Git Hub. The CUDA Runtime API wraps the CUDA Driver API and provides a higher-level API for the same fu…
- What is the CUDA Driver API? (Modal)Click this button to let us know on Git Hub. The CUDA Driver API is the userspace component of the NVIDIA CUDA drivers.
- What is Streaming Assembler? (Modal)Click this button to let us know on Git Hub. Streaming ASSembler (SASS) is the assembly format for programs running on NVIDIA GPUs.
- What does it mean to be compute-bound? (Modal)Click this button to let us know on Git Hub. Kernels that are compute-bound are limited by the arithmetic bandwidth of the CUDA Cores or Te…
- What is cuTile BASIC? (Modal)Click this button to let us know on Git Hub. cu Tile BASIC is an implementation of the CUDA Tile programming model in the BASIC programming…
- What is latency hiding? (Modal)Click this button to let us know on Git Hub. Latency hiding is a strategy to mask long-latency operations by running many of them concurren…
- What is SM utilization? (Modal)Click this button to let us know on Git Hub. SM utilization measures the percentage of time that Streaming Multiprocessors (SMs) are execut…
- What is a CUDA Kernel? (Modal)Click this button to let us know on Git Hub. A kernel is the unit of CUDA code that programmers typically write and compose, akin to a proc…
- What is Compute Capability? (Modal)Click this button to let us know on Git Hub. Instructions in the Parallel Thread Execution instruction set are compatible with only certain…
- What is branch efficiency? (Modal)Click this button to let us know on Git Hub. Branch efficiency measures how often all threads in a warp take the same execution path when e…
- What is a Cooperative Thread Array? (Modal)Click this button to let us know on Git Hub. A cooperative thread array (CTA) is a collection of threads scheduled onto the same Streaming…
- What is arithmetic bandwidth? (Modal)Click this button to let us know on Git Hub. Arithmetic bandwidth is the peak rate at which arithmetic work can be performed by a system.
- What is a Tensor Memory Accelerator? (Modal)Click this button to let us know on Git Hub. Tensor Memory Accelerators are specialized hardware in Hopper and Blackwell architecture GPUs…
- What is nvidia.ko? (Modal)Click this button to let us know on Git Hub. Click this button to let us know on Git Hub.
- What is a bank conflict? (Modal)Click this button to let us know on Git Hub. When multiple threads in a warp simultaneously request memory within the same bank in shared m…
- What is libcuda.so? (Modal)Click this button to let us know on Git Hub. Click this button to let us know on Git Hub.
- What is a Warpgroup? (Modal)Click this button to let us know on Git Hub. A warpgroup is a set of four contiguous warps such that the warp-rank of the first warp is a m…
- What is issue efficiency? (Modal)Click this button to let us know on Git Hub. Issue efficiency measures how effectively the warp scheduler keeps execution pipes busy by iss…
- What is a Register File? (Modal)Click this button to let us know on Git Hub. The register file of the Streaming Multiprocessor is the primary store of bits in between thei…
- What is a CUDA Graph? (Modal)Click this button to let us know on Git Hub. A CUDA Graph is a graph of kernel launches and other work that can be submitted by the host to…
- What is CuTe DSL? (Modal)Click this button to let us know on Git Hub. Cu Te DSL is a Python-based Domain-Specific Language (DSL) for writing and dynamically compili…
- What is GPU RAM? (Modal)Click this button to let us know on Git Hub. The bottom-level memory of the GPU is a large (many megabytes to gigabytes) memory store that…
- What is NVIDIA Nsight Systems? (Modal)Click this button to let us know on Git Hub. NVIDIA Nsight Systems is a performance debugging tool for CUDA C++ programs.
- What is warp execution state? (Modal)Click this button to let us know on Git Hub. The state of the warps running a kernel is described with a number of non-exclusive adjectives…
- current_function_call_id (Modal)Returns the function call ID for the current input.
- What is register pressure? (Modal)Click this button to let us know on Git Hub. Register pressure is a colorful term used when the register file is a bottleneck .
- What is a Thread Block Grid? (Modal)Click this button to let us know on Git Hub. When a CUDA kernel is launched, it creates a collection of threads known as a thread block gri…
- What is a Texture Processing Cluster? (Modal)Click this button to let us know on Git Hub. A Texture Processing Cluster (TPC) is a pair of adjacent Streaming Multiprocessors (SMs) .
- What is a GPU Core? (Modal)Click this button to let us know on Git Hub. The cores are the primary compute units that make up the Streaming Multiprocessors (SMs) .
- modal profile (Modal)modal profile Switch between Modal profiles. Usage: modal profile [OPTIONS] COMMAND [ARGS]...
- What is a Warp? (Modal)Click this button to let us know on Git Hub. A warp is a group of threads that are scheduled together and execute in parallel.
- modal billing (Modal)modal billing View workspace billing information. Usage: modal billing [OPTIONS] COMMAND [ARGS]...
- modal function (Modal)Usage: modal function [OPTIONS] COMMAND [ARGS]... Options: - --help : Show this message and exit.
- What is a performance bottleneck? (Modal)Click this button to let us know on Git Hub. The literal neck of a bottle limits the rate at which liquid can be poured; a metaphorical per…
- What is the CUDA Programming Model? (Modal)Click this button to let us know on Git Hub. The CUDA programming model is a programming model for programming massively parallel processor…
- What is a CUDA Device Architecture? (Modal)Click this button to let us know on Git Hub. CUDA stands for Compute Unified Device Architecture.