CubeCL
Shares rank 10 of 12 GPU compute frameworks by recommenders
People recommend it for running Rust GPU kernels on WebGPU, Vulkan, CUDA, ROCm and Metal; the main caveat is thin documentation.
People recommend it for running Rust GPU kernels on WebGPU, Vulkan, CUDA, ROCm and Metal; the main caveat is thin documentation.
7 people gave an opinion
- recommend it
- 5
- criticize it
- 2
- approval share
- 71%
Recommended in 4 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: recommended
- April 2026: not recommended
- May 2026: not recommended
- June 2026: recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 5 people recommend itNeeds 10 or more, not met.
- 2.5 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 4 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Targets many GPU backends
“it supports WebGPU through WGSL and Vulkan through SPIR-V, along with CUDA, AMD via ROCm, and Metal”
Comment from 17 Sep 2026 in “Nvidia announces native GPU programming in Rust” Rust macros for GPU kernels
“Still blows my mind that they basically implemented a subset of Rust inside of a Rust macro”
Comment from 17 Jun 2026 in “Show HN: cuTile Rust: Safe, data-race-free GPU kernels in Rust” “this is basically exactly what CubeCL does”
Comment from 8 Mar 2026 in “Show HN: Eyot, A programming language where the GPU is just another thread” Mojo-style GPU programming in Rust
“if you want Mojo in Rust there is”
Comment from 4 Oct 2026 in “Vx – One Language, Every Chip”
What people warn about
Each mark is one comment
Thin documentation
“lack of documentation and my lack of experience”
Comment from 14 Apr 2026 in “Rust Threads on the GPU” Dependency seen as not ideal
“pulling in CubeCL as a dependency is... not ideal.”
Comment from 1 Jul 2026 in “From Julia to Rust: a differentiable tensor stack for scientific computing”
Other GPU compute frameworks people recommend
The four most recommended other GPU compute frameworks, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| NVIDIA CUDA | 91 | 73 | 55% | 12 | 18 yrs3 owners | — |
| AMD ROCm | 47 | 97 | 33% | 11 | 3 yrs4 owners | — |
| BarraCUDA | 21 | 7 | 75% | 2 | — | — |
| Triton | 18 | 2 | 90% | 8 | — | Approved |
| CubeCLThis page | 5 | 2 | 71% | 4 | — | — |
What people said
6 of the 7 comments that mention it, newest first. Each links to the original comment.
“if you want Mojo in Rust there is”
“it supports WebGPU through WGSL and Vulkan through SPIR-V, along with CUDA, AMD via ROCm, and Metal”
“pulling in CubeCL as a dependency is... not ideal.”
“Still blows my mind that they basically implemented a subset of Rust inside of a Rust macro”
“lack of documentation and my lack of experience”
“this is basically exactly what CubeCL does”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.