Pedro Augusto 2b33c15277 sparse/attention: drop FUSED_ATTN_MAX_SEQLEN threshold to match CUDA-path precedent ... The 256-cap inside the flex_gemm_sparse_attn branch was a hold-over from the early naive Metal kernel (round 3). The current backend is flash- attention-v2 with simdgroup matmul + simd-shuffle softmax row reductions and wins at every measured shape including max_seqlen=2048. The CUDA backends above (xformers / flash_attn / flash_attn_3) never fork on max_seqlen — match that precedent. Safety-valve preserved as FLEX_GEMM_ATTN_MAX_SEQLEN=N env var: when set, falls back to SDPA-padded above the cap. Useful only on PyTorch builds where the Accelerate-SDPA-CPU-bounce happens to win at a specific shape (measured crossover sits beyond 768 on fp32, higher on fp16).		2026-07-17 07:51:05 +03:00
..
__init__.py	Init Release	2025-12-16 19:00:42 +00:00
full_attn.py	sparse/attention: drop FUSED_ATTN_MAX_SEQLEN threshold to match CUDA-path precedent	2026-07-17 07:51:05 +03:00
modules.py	Init Release	2025-12-16 19:00:42 +00:00
rope.py	Init Release	2025-12-16 19:00:42 +00:00
windowed_attn.py	add mlx backend for apple silicon with metal gpu acceleration	2026-07-17 07:51:05 +03:00