Rust-GPU · LegNeato · Sep 17, 2025 · Sep 16, 2025 · Sep 16, 2025 · Sep 16, 2025
diff --git a/README.md b/README.md
@@ -61,7 +61,7 @@ The current line-up of libraries is the following:
 - `cuda_std` for GPU-side functions and utilities, such as thread index queries, memory allocation, warp intrinsics, etc.
   - _Not_ a low level library, provides many utility functions to make it easier to write cleaner and more reliable GPU kernels.
   - Closely tied to `rustc_codegen_nvvm` which exposes GPU features through it internally.
-- [`cudnn`](https://github.com/Rust-GPU/Rust-CUDA/tree/master/crates/cudnn) for a collection of GPU-accelerated primitives for deep neural networks.
+- [`cudnn`](https://github.com/Rust-GPU/rust-cuda/tree/master/crates/cudnn) for a collection of GPU-accelerated primitives for deep neural networks.
 - `cust` for CPU-side CUDA features such as launching GPU kernels, GPU memory allocation, device queries, etc.
   - High level with features such as RAII and Rust Results that make it easier and cleaner to manage the interface to the GPU.
   - A high level wrapper for the CUDA Driver API, the lower level version of the more common CUDA Runtime API used from C++.
@@ -92,7 +92,7 @@ Other projects related to using Rust on the GPU:
 cargo build
 ```
 
-## Use Rust-CUDA in Container Environments
+## Use Rust CUDA in Container Environments
 
 The distribution related Dockerfile are located in `container` folder.
 Taking ubuntu 24.04 as an example, run the following command in repository root:

diff --git a/container/rockylinux9-cuda12/Dockerfile b/container/rockylinux9-cuda12/Dockerfile
@@ -72,8 +72,8 @@ RUN curl -sSf -L https://sh.rustup.rs | bash -s -- -y
 ENV PATH="/root/.cargo/bin:${PATH}"
 
 # Setup the workspace
-WORKDIR /data/Rust-CUDA
-RUN --mount=type=bind,source=rust-toolchain.toml,target=/data/Rust-CUDA/rust-toolchain.toml \
+WORKDIR /data/rust-cuda
+RUN --mount=type=bind,source=rust-toolchain.toml,target=/data/rust-cuda/rust-toolchain.toml \
     rustup show
 
 # Add nvvm to LD_LIBRARY_PATH.

diff --git a/container/ubuntu22-cuda11/Dockerfile b/container/ubuntu22-cuda11/Dockerfile
@@ -71,8 +71,8 @@ RUN curl -sSf -L https://sh.rustup.rs | bash -s -- -y
 ENV PATH="/root/.cargo/bin:${PATH}"
 
 # Setup the workspace
-WORKDIR /data/Rust-CUDA
-RUN --mount=type=bind,source=rust-toolchain.toml,target=/data/Rust-CUDA/rust-toolchain.toml \
+WORKDIR /data/rust-cuda
+RUN --mount=type=bind,source=rust-toolchain.toml,target=/data/rust-cuda/rust-toolchain.toml \
     rustup show
 
 # Add nvvm to LD_LIBRARY_PATH.

diff --git a/container/ubuntu22-cuda12/Dockerfile b/container/ubuntu22-cuda12/Dockerfile
@@ -71,8 +71,8 @@ RUN curl -sSf -L https://sh.rustup.rs | bash -s -- -y
 ENV PATH="/root/.cargo/bin:${PATH}"
 
 # Setup the workspace
-WORKDIR /data/Rust-CUDA
-RUN --mount=type=bind,source=rust-toolchain.toml,target=/data/Rust-CUDA/rust-toolchain.toml \
+WORKDIR /data/rust-cuda
+RUN --mount=type=bind,source=rust-toolchain.toml,target=/data/rust-cuda/rust-toolchain.toml \
     rustup show
 
 # Add nvvm to LD_LIBRARY_PATH.

diff --git a/container/ubuntu24-cuda12/Dockerfile b/container/ubuntu24-cuda12/Dockerfile
@@ -71,8 +71,8 @@ RUN curl -sSf -L https://sh.rustup.rs | bash -s -- -y
 ENV PATH="/root/.cargo/bin:${PATH}"
 
 # Setup the workspace
-WORKDIR /data/Rust-CUDA
-RUN --mount=type=bind,source=rust-toolchain.toml,target=/data/Rust-CUDA/rust-toolchain.toml \
+WORKDIR /data/rust-cuda
+RUN --mount=type=bind,source=rust-toolchain.toml,target=/data/rust-cuda/rust-toolchain.toml \
     rustup show
 
 # Add nvvm to LD_LIBRARY_PATH.

diff --git a/crates/blastoff/Cargo.toml b/crates/blastoff/Cargo.toml
@@ -3,7 +3,7 @@ name = "blastoff"
 version = "0.1.0"
 edition = "2021"
 authors = ["Riccardo D'Ambrosio <[email protected]>"]
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 
 [dependencies]
 bitflags = "2.8"

diff --git a/crates/cuda_builder/Cargo.toml b/crates/cuda_builder/Cargo.toml
@@ -5,7 +5,7 @@ edition = "2021"
 authors = ["Riccardo D'Ambrosio <[email protected]>", "The rust-gpu Authors"]
 license = "MIT OR Apache-2.0"
 description = "Builder for easily building rustc_codegen_nvvm crates"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 
 [dependencies]

diff --git a/crates/cuda_std/Cargo.toml b/crates/cuda_std/Cargo.toml
@@ -4,7 +4,7 @@ version = "0.2.2"
 edition = "2018"
 license = "MIT OR Apache-2.0"
 description = "Standard library for CUDA with rustc_codegen_nvvm"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 
 [dependencies]

diff --git a/crates/cuda_std_macros/Cargo.toml b/crates/cuda_std_macros/Cargo.toml
@@ -4,7 +4,7 @@ version = "0.2.0"
 edition = "2018"
 license = "MIT OR Apache-2.0"
 description = "Macros for cuda_std"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 
 [lib]

diff --git a/crates/cudnn-sys/Cargo.toml b/crates/cudnn-sys/Cargo.toml
@@ -3,7 +3,7 @@ name = "cudnn-sys"
 version = "0.1.0"
 edition = "2024"
 license = "MIT OR Apache-2.0"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 links = "cudnn"
 build = "build/main.rs"

diff --git a/crates/cust/CHANGELOG.md b/crates/cust/CHANGELOG.md
@@ -145,7 +145,7 @@ it much easier to write multigpu code. The CUDA API is fully thread-safe except
 - Added `MemoryAdvise::advise_read_mostly`.
 - Added `MemoryAdvise::preferred_location` and `MemoryAdvise::unset_preferred_location`.
 Note that advising APIs are only present on high end GPUs such as V100s.
-- `StreamFlags::NON_BLOCKING` has been temporarily disabled because of [soundness concerns](https://github.com/Rust-GPU/Rust-CUDA/issues/15).
+- `StreamFlags::NON_BLOCKING` has been temporarily disabled because of [soundness concerns](https://github.com/Rust-GPU/rust-cuda/issues/15).
 
 ## 0.2.0 - 11/26/21
 

diff --git a/crates/cust/Cargo.toml b/crates/cust/Cargo.toml
@@ -9,7 +9,7 @@ authors = [
 edition = "2021"
 license = "MIT OR Apache-2.0"
 description = "High level bindings to the CUDA Driver API"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 
 [dependencies]

diff --git a/crates/cust/src/stream.rs b/crates/cust/src/stream.rs
@@ -30,7 +30,7 @@ bitflags::bitflags! {
 
         /// This stream does not synchronize with the NULL stream.
         ///
-        /// **Note: this flag has been temporarily disabled because of [soundness concerns](https://github.com/Rust-GPU/Rust-CUDA/issues/15)**
+        /// **Note: this flag has been temporarily disabled because of [soundness concerns](https://github.com/Rust-GPU/rust-cuda/issues/15)**
         ///
         /// Note that the name is chosen to correspond to CUDA documentation, but is nevertheless
         /// misleading. All work within a single stream is ordered and asynchronous regardless
@@ -93,7 +93,7 @@ impl Stream {
     /// # }
     /// ```
     pub fn new(mut flags: StreamFlags, priority: Option<i32>) -> CudaResult<Self> {
-        // NOTE(RDambrosio016): See https://github.com/Rust-GPU/Rust-CUDA/issues/15
+        // NOTE(RDambrosio016): See https://github.com/Rust-GPU/rust-cuda/issues/15
         flags.remove(StreamFlags::NON_BLOCKING);
         unsafe {
             let mut stream = Stream {

diff --git a/crates/cust_core/Cargo.toml b/crates/cust_core/Cargo.toml
@@ -4,7 +4,7 @@ version = "0.1.1"
 edition = "2021"
 license = "MIT OR Apache-2.0"
 description = "Core library for cust that can be shared across CPU and GPU"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 
 [dependencies]

diff --git a/crates/cust_derive/Cargo.toml b/crates/cust_derive/Cargo.toml
@@ -5,7 +5,7 @@ authors = ["Brook Heisler <[email protected]>", "Riccardo D'Ambrosio <rdamb
 edition = "2018"
 license = "MIT OR Apache-2.0"
 description = "Macros for cust"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 
 [lib]

diff --git a/crates/cust_raw/Cargo.toml b/crates/cust_raw/Cargo.toml
@@ -4,7 +4,7 @@ version = "0.11.3"
 edition = "2021"
 license = "MIT OR Apache-2.0"
 description = "Low level bindings to the CUDA Driver API"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 links = "cuda"
 build = "build/main.rs"

diff --git a/crates/gpu_rand/Cargo.toml b/crates/gpu_rand/Cargo.toml
@@ -5,7 +5,7 @@ authors = ["The Rand Project Developers", "The Rust CUDA Project Developers"]
 license = "MIT OR Apache-2.0"
 edition = "2021"
 description = "GPU-friendly random number generators for the Rust CUDA Project"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 
 [dependencies]

diff --git a/crates/nvvm/Cargo.toml b/crates/nvvm/Cargo.toml
@@ -5,7 +5,7 @@ authors = ["Riccardo D'Ambrosio <[email protected]>"]
 edition = "2018"
 license = "MIT OR Apache-2.0"
 description = "High level bindings to libnvvm"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 
 [dependencies]

diff --git a/crates/optix-sys/Cargo.toml b/crates/optix-sys/Cargo.toml
@@ -3,7 +3,7 @@ name = "optix-sys"
 version = "0.1.0"
 edition = "2024"
 license = "MIT OR Apache-2.0"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 links = "optix"
 build = "build/main.rs"

diff --git a/crates/optix/Cargo.toml b/crates/optix/Cargo.toml
@@ -3,7 +3,7 @@ name = "optix"
 version = "0.1.0"
 edition = "2021"
 license = "MIT OR Apache-2.0"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 authors = ["Anders Langlands <[email protected]>", "Riccardo D'Ambrosio <[email protected]>"]
 

diff --git a/crates/optix_device_macros/Cargo.toml b/crates/optix_device_macros/Cargo.toml
@@ -4,7 +4,7 @@ version = "0.1.0"
 edition = "2018"
 license = "MIT OR Apache-2.0"
 description = "Macros for optix_device"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 
 [lib]

diff --git a/crates/ptx/Cargo.toml b/crates/ptx/Cargo.toml
@@ -4,7 +4,7 @@ version = "0.1.0"
 edition = "2018"
 license = "MIT OR Apache-2.0"
 description = "PTX parser and analyzer"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 
 [dependencies]

diff --git a/crates/ptx_compiler/Cargo.toml b/crates/ptx_compiler/Cargo.toml
@@ -4,7 +4,7 @@ version = "0.1.1"
 edition = "2021"
 license = "MIT OR Apache-2.0"
 description = "High level bindings to CUDA's ptx compilation APIs"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 
 [dependencies]

diff --git a/crates/rustc_codegen_nvvm/Cargo.toml b/crates/rustc_codegen_nvvm/Cargo.toml
@@ -8,7 +8,7 @@ authors = [
 edition = "2024"
 license = "MIT OR Apache-2.0"
 description = "A codegen backend for Rustc which targets the libnvvm CUDA library"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 
 [lib]

diff --git a/crates/rustc_codegen_nvvm/src/builder.rs b/crates/rustc_codegen_nvvm/src/builder.rs
@@ -213,9 +213,9 @@ macro_rules! math_builder_methods {
                     _ => {
                         self.cx.fatal(format!(
                             "Unimplemented 128-bit integer operation '{}' with {} arguments. \
-                             This operation is not yet supported in Rust-CUDA. \
+                             This operation is not yet supported in Rust CUDA. \
                              Consider using 64-bit integers or filing an issue at \
-                             https://github.com/Rust-GPU/Rust-CUDA/issues",
+                             https://github.com/Rust-GPU/rust-cuda/issues",
                             stringify!($name),
                             args_vec.len()
                         ));

diff --git a/crates/rustc_codegen_nvvm/src/lib.rs b/crates/rustc_codegen_nvvm/src/lib.rs
@@ -89,7 +89,7 @@ use std::ffi::CString;
 #[unsafe(no_mangle)]
 pub fn __rustc_codegen_backend() -> Box<dyn CodegenBackend> {
     rustc_driver::install_ice_hook(
-        "https://github.com/Rust-GPU/Rust-CUDA/issues/new",
+        "https://github.com/Rust-GPU/rust-cuda/issues/new",
         |handler| {
             handler.handle().note(concat!(
                 "`rust-cuda` version `",

diff --git a/crates/rustc_codegen_nvvm_macros/Cargo.toml b/crates/rustc_codegen_nvvm_macros/Cargo.toml
@@ -4,7 +4,7 @@ version = "0.1.0"
 edition = "2021"
 license = "MIT OR Apache-2.0"
 description = "Macros for rustc_codegen_nvvm"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 
 [lib]

diff --git a/examples/cuda/gemm/src/main.rs b/examples/cuda/gemm/src/main.rs
@@ -1,4 +1,4 @@
-//! Example demonstrating GEMM (General Matrix Multiply) on CUDA using Rust-CUDA.
+//! Example demonstrating GEMM (General Matrix Multiply) on CUDA using Rust CUDA.
 //!
 //! This example benchmarks naive and tiled GEMM kernels as well as cuBLAS for various matrix sizes.
 //! It uses the `cust` crate for CUDA management and `ndarray` for host-side matrix operations.

diff --git a/guide/src/guide/getting_started.md b/guide/src/guide/getting_started.md
@@ -9,7 +9,7 @@ Before you can use the project to write GPU crates, you will need a couple of pr
 - [The CUDA SDK](https://developer.nvidia.com/cuda-downloads), version `11.2-11.8` (and the appropriate driver - [see cuda release notes](https://docs.nvidia.com/cuda/cuda-toolkit-release-notes/index.html)).
 
   - We recently [added experimental support for the `12.x`
-    SDK](https://github.com/Rust-GPU/Rust-CUDA/issues/100), please file any issues you
+    SDK](https://github.com/Rust-GPU/rust-cuda/issues/100), please file any issues you
     see
 
   This is only for building GPU crates, to execute built PTX you only need CUDA `9+`.
@@ -234,7 +234,7 @@ components = ["rust-src", "rustc-dev", "llvm-tools-preview"]
 
 There is also a [Dockerfile](Dockerfile) prepared as a quickstart with all the necessary libraries for base cuda development.
 
-You can use it as follows (assuming your clone of Rust-CUDA is at the absolute path `RUST_CUDA`):
+You can use it as follows (assuming your clone of Rust CUDA is at the absolute path `RUST_CUDA`):
 
 - Ensure you have Docker setup to [use gpus](https://docs.docker.com/config/containers/resource_constraints/#gpu)
 - Build `docker build -t rust-cuda $RUST_CUDA`

diff --git a/tests/compiletests/README.md b/tests/compiletests/README.md
@@ -1,6 +1,6 @@
-# Compiletests for Rust-CUDA
+# Compiletests for Rust CUDA
 
-This directory contains compile tests for the Rust-CUDA project using the `compiletest` framework.
+This directory contains compile tests for the Rust CUDA project using the `compiletest` framework.
 
 The code in these tests is not executed. Tests check that the compiler compiles
 correctly. Tests in `dis/` verify correct PTX output.

diff --git a/tests/compiletests/src/main.rs b/tests/compiletests/src/main.rs
@@ -65,7 +65,7 @@ fn main() {
 
     // HACK(eddyb) force `compiletest` to pass `ui/...` relative paths to `rustc`,
     // which should always end up being the same regardless of the path that the
-    // Rust-CUDA repo is checked out at (among other things, this avoids hardcoded
+    // Rust CUDA repo is checked out at (among other things, this avoids hardcoded
     // `compiletest` limits being hit by e.g. users with slightly longer paths).
     std::env::set_current_dir(tests_dir).unwrap();
     let tests_dir = PathBuf::from("");