Writing the low-level code that runs on GPUs, with tools like CUDA, Triton and custom kernels. A well-written kernel can make a model train or run many times faster on the same hardware. AI is now even being used to write these kernels itself.
66 stories so far in 2026
Stories per month in 2026| Month | Stories |
|---|
| January | 0 |
|---|
| February | 0 |
|---|
| March | 0 |
|---|
| April | 3 |
|---|
| May | 1 |
|---|
| June | 17 |
|---|
| July | 5 |
|---|
| August | 3 |
|---|
| September | 12 |
|---|
| October | 17 |
|---|
| November | 8 |
|---|
| December | 0 |
|---|