biondizzle 89510601f5 Revert compressor pos bias fix + SwiGLU clamp ordering from commit 3320abf ...

These changes were made based on CORRECTNESS_FIX_ATTEMPTS.md but the
PyTorch reference (which works correctly) doesn't have them. Reverting
to match the reference behavior:
- Compressor: position bias added to BOTH gate logits AND KV content
- SwiGLU: clamp after silu(gate), not before

2026-06-03 13:57:16 +00:00

..

_archive

Cleanup Step 2: Archive Lineage P code, fix broken imports

2026-06-02 19:27:07 +00:00

cache

Cleanup Step 2: Archive Lineage P code, fix broken imports

2026-06-02 19:27:07 +00:00

kernels

Revert compressor pos bias fix + SwiGLU clamp ordering from commit 3320abf

2026-06-03 13:57:16 +00:00

layers

Revert compressor pos bias fix + SwiGLU clamp ordering from commit 3320abf

2026-06-03 13:57:16 +00:00

loader

Cleanup Step 2: Archive Lineage P code, fix broken imports

2026-06-02 19:27:07 +00:00

model

Cleanup Step 2: Archive Lineage P code, fix broken imports

2026-06-02 19:27:07 +00:00

ops

Fix non-contiguous tensor in quantize_nvfp4_gpu_fused (T>1 prefill)

2026-06-03 07:56:19 +00:00

reference

Update PyTorch reference with official DSV4 encoding + batched prefill

2026-06-03 12:19:38 +00:00

__init__.py

Restructure: cutedsl/ -> dsv4/ with proper layering

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