Files
foxhunt/crates
jgrusewski 76fdd155a1 fix(cuda): compile to native cubin instead of PTX — eliminate driver JIT entirely
nvcc now produces cubin (native SASS) with -cubin -arch=sm_XX instead of
PTX with -ptx -arch=compute_XX. cuModuleLoad() loads SASS directly — zero
driver JIT. TMA instructions (cp.async.bulk on sm_90+) work natively because
nvcc handles them during offline compilation. Removed TMA fallback from
experience collector (double-compile + 15s retry overhead eliminated).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-15 14:32:53 +01:00
..