biondizzle e91421f06e Fix KV cache page size patch: separate groups for large SWA pages

2026-05-19 09:05:14 +00:00

..

fused_moe

Fix activation global scale: don't double-invert input_global_scale_inv

2026-05-19 06:03:08 +00:00

layers

Fix KV cache crash: skip SWA cache write on Blackwell

2026-05-19 08:21:57 +00:00

deepseek_v4_attention.py

Add CuTeDSL NVFP4 attention kernel test - Q×K^T GEMM

2026-05-19 08:54:59 +00:00

deepseek_v4.py

Fix hc_head mapping: checkpoint uses hc_head.hc_fn, model params are flat hc_head_fn

2026-05-19 03:58:25 +00:00

kernel.py

Add cutedsl to MoEBackend type in kernel config

2026-05-18 22:38:41 +00:00

patch_kv_cache_utils.py

Fix KV cache page size patch: separate groups for large SWA pages

2026-05-19 09:05:14 +00:00

register_cutedsl_kernel.py

Fix Blackwell: skip FlashMLA assertion + force CuTeDSL kernel

2026-05-19 08:19:23 +00:00