qutaoandClaude Opus 4.8 d3de762ce2 Merge origin/main into nvf4-block-scale-sm120 ...

Resolve conflicts in merge_shared_memory_allocations.cc and codegen_cuda.cc:
upstream's new shared common/storage_size.h GetBufferStorageSizeBytes helper
covers the packed-FP4 exact-bits sizing this branch introduced (and extends
it to 4-bit integer types), so the sizing conflicts take the upstream side
and the branch-local sizing helpers are dropped. The NVFP4
byte-offset -> logical-index conversion in the non-alias rewrite stays, as
upstream has no equivalent. codegen_cuda.cc's 4-bit shared-allocation
handling was equivalently refactored upstream (is_byte_packed_4bit) and
already includes the scalar float4_e2m1fn case.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-07-21 18:56:30 +08:00

..

test_tilelang_quantize_fp8.py

[BugFix] Decode FP8 E4M3 special encodings correctly (#2710)

2026-07-20 14:06:46 +08:00

test_tilelang_quantize_nvfp4_scale_layout.py

Group SM120 NVFP4 maint files and use native target API

2026-07-21 16:56:18 +08:00