biondizzle 5e3ced0b60 DEBUG: isolate which kernel causes cudaErrorInvalidValue in SE L2 path

2026-06-04 00:41:28 +00:00

..

__init__.py

Restructure: cutedsl/ -> dsv4/ with proper layering

2026-05-21 17:30:44 +00:00

grouped_linear.py

Fix gsa copy_ cudaErrorInvalidValue: replace view-based copy_ with scalar assignment

2026-06-04 00:30:21 +00:00

linear.py

Fix gsa copy_ cudaErrorInvalidValue: replace view-based copy_ with scalar assignment

2026-06-04 00:30:21 +00:00

mhc.py

CUDA graph: Fix per-step allocations in decode loop

2026-06-03 16:38:35 +00:00

moe.py

Fix gsa copy_ cudaErrorInvalidValue: replace view-based copy_ with scalar assignment

2026-06-04 00:30:21 +00:00

router.py

CRITICAL FIX: runtime activation global scale to prevent E4M3 overflow

2026-06-01 14:21:16 +00:00

shared_expert.py

DEBUG: isolate which kernel causes cudaErrorInvalidValue in SE L2 path

2026-06-04 00:41:28 +00:00