jgrusewski 4223ba676f fix(build): fat cubins sm_86+sm_89+sm_90 — RTX 3050 + L40S + H100 ...

Replace -cubin -arch=sm_XX with -fatbin -gencode for all 3 GPU archs.
All include_bytes! paths updated from .cubin to .fatbin. Removes
CUDA_COMPUTE_CAP env var dependency. cuModuleLoadData transparently
selects the right arch from the fat binary at runtime.

Fixes CUDA_ERROR_NO_BINARY_FOR_GPU on H100 (sm_90).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-05-26 11:58:14 +02:00

..

cuda

feat(rl): outcome head backward + diag JSONL enrichment

2026-05-26 11:47:19 +02:00

examples

feat(rl): outcome head backward + diag JSONL enrichment

2026-05-26 11:47:19 +02:00

src

fix(build): fat cubins sm_86+sm_89+sm_90 — RTX 3050 + L40S + H100

2026-05-26 11:58:14 +02:00

tests

test(rl): GPU oracle tests for IQN + NoisyNet + PRNG advance fix

2026-05-25 22:37:40 +02:00

build.rs

fix(build): fat cubins sm_86+sm_89+sm_90 — RTX 3050 + L40S + H100

2026-05-26 11:58:14 +02:00

Cargo.toml

feat(rl): R6 — replace LobEnv with kernel-driven GPU-pure env step

2026-05-23 10:39:25 +02:00