biondizzle e671780008 fix: transpose checkpoint weights before make_b_k_major in Nvfp4Linear/SharedExpert ...

Critical bug: checkpoint weights are (N_packed, K_packed) N-major format,
but make_b_k_major expects (E, K_packed, N_packed) input. Without the
permute, the K and N dimensions are swapped, producing garbage output
with wrong dimensions (e.g., q_a output was 3584 instead of 1536).

Also fix scale assembly: checkpoint scales are (N, K_sf) which should
use assemble_raw_scales_2d3d_3d_side (no transpose), not
assemble_scales_3d_side (which incorrectly transposes K_sf↔N).

2026-06-01 00:30:37 +00:00

..

__init__.py

Restructure: cutedsl/ -> dsv4/ with proper layering

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

attention.py

E2/E3: compressor bridge, indexer bridge, flush pipeline wiring

2026-05-30 21:16:54 +00:00

embedding.py

Restructure: cutedsl/ -> dsv4/ with proper layering

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

ffn.py

Layer dispatch: config, schedule, attention/FFN sub-blocks, TransformerLayer

2026-05-21 23:11:09 +00:00

grouped_linear.py

Restructure: cutedsl/ -> dsv4/ with proper layering

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

linear.py

fix: transpose checkpoint weights before make_b_k_major in Nvfp4Linear/SharedExpert

2026-06-01 00:30:37 +00:00

mhc.py

Add --no-thinking mode to skip thinking tokens and use second-best

2026-05-31 19:24:21 +00:00

moe.py

fix: convert uint8 checkpoint weights to float4_e2m1fn_x2 for CuTeDSL GEMM

2026-06-01 00:18:34 +00:00

norm.py

Fix layer construction: match existing API signatures, add RMSNorm impl

2026-05-21 23:31:58 +00:00

router.py

Router: full kernel stack — hash, topk, activation+topk, dense decode/prefill

2026-05-21 21:54:05 +00:00

shared_expert.py

fix: transpose checkpoint weights before make_b_k_major in Nvfp4Linear/SharedExpert

2026-06-01 00:30:37 +00:00