Open Issues Need Help
View All on GitHub tma_multicast's README still says consumer Blackwell cannot run it, which #668 measured and corrected everywhere else about 2 months ago
good first issue
NVlabs/cuda-oxide NVlabs/cuda-oxide cuda-oxide is an experimental Rust-to-CUDA compiler that lets you write (SIMT) GPU kernels in safe(ish), idiomatic Rust. It compiles standard Rust code directly to PTX — no DSLs, no foreign language bindings, just Rust.
Open project →
3.0K
cuda-oxide is an experimental Rust-to-CUDA compiler that lets you write (SIMT) GPU kernels in safe(ish), idiomatic Rust. It compiles standard Rust code directly to PTX — no DSLs, no foreign language bindings, just Rust.
Rust
#async#compiler-backend#cuda#gpu#heterogeneous-computing#high-performance-computing#nvidia#programming-languages#rust
bug good first issue examples
NVlabs/cuda-oxide NVlabs/cuda-oxide cuda-oxide is an experimental Rust-to-CUDA compiler that lets you write (SIMT) GPU kernels in safe(ish), idiomatic Rust. It compiles standard Rust code directly to PTX — no DSLs, no foreign language bindings, just Rust.
Open project →
3.0K
cuda-oxide is an experimental Rust-to-CUDA compiler that lets you write (SIMT) GPU kernels in safe(ish), idiomatic Rust. It compiles standard Rust code directly to PTX — no DSLs, no foreign language bindings, just Rust.
Rust
#async#compiler-backend#cuda#gpu#heterogeneous-computing#high-performance-computing#nvidia#programming-languages#rust
Value-threaded WGMMA accumulator lowering for pipelined use (wait_group<N>, multiple groups in flight) 3 months ago
enhancement help wanted perf IR-lowering cuda-feature wgmma-value-path
NVlabs/cuda-oxide NVlabs/cuda-oxide cuda-oxide is an experimental Rust-to-CUDA compiler that lets you write (SIMT) GPU kernels in safe(ish), idiomatic Rust. It compiles standard Rust code directly to PTX — no DSLs, no foreign language bindings, just Rust.
Open project →
3.0K
cuda-oxide is an experimental Rust-to-CUDA compiler that lets you write (SIMT) GPU kernels in safe(ish), idiomatic Rust. It compiles standard Rust code directly to PTX — no DSLs, no foreign language bindings, just Rust.
Rust
#async#compiler-backend#cuda#gpu#heterogeneous-computing#high-performance-computing#nvidia#programming-languages#rust