3 people f38836d14d cuda: pass kernel dynamic shared memory in the graph runner (#16699) ...

The CUDA graph runner hardcoded sharedMemBytes=0 in the kernel node params, so a custom_kernel
using dynamic shared memory (extern __shared__) failed with CUDA error 700 on graph replay
while the eager path worked. Pass runtime.smem (0 for normal kernels, which use static shared).

Co-authored-by: Claude Opus 4.8 (1M context) <[email protected]>

2026-06-24 14:20:10 +03:00

..

__init__.py

missing init files (#5196)

2024-06-27 15:30:02 -04:00

cuda.py

cuda: pass kernel dynamic shared memory in the graph runner (#16699)

2026-06-24 14:20:10 +03:00

hcq.py

remove many type ignores [PR] (#16652)

2026-06-17 21:38:45 -04:00

metal.py

rename BUFFER_VIEW to SLICE (#16391)

2026-05-26 18:15:00 -07:00