yzwu 8b890c0d72 [Iluvatar] refactor attn and moe code (#6887)

2026-03-18 10:31:00 +08:00

..

__init__.py

…

base.py

[Models][OP][Optimization] Support DeepSeek-v3.2 model, integrate DSA & Indexer architecture with FlashMLA/DeepGEMM (#6689)

2026-03-10 15:05:14 +08:00

cpu.py

…

cuda.py

[Models][OP][Optimization] Support DeepSeek-v3.2 model, integrate DSA & Indexer architecture with FlashMLA/DeepGEMM (#6689)

2026-03-10 15:05:14 +08:00

dcu.py

…

gcu.py

…

iluvatar.py

[Iluvatar] refactor attn and moe code (#6887)

2026-03-18 10:31:00 +08:00

intel_hpu.py

[Intel HPU] enable tensor_wise_fp8 (#5324)

2025-12-17 16:45:03 +08:00

maca.py

…

npu.py

…

utils.py

…

xpu.py

[XPU] move xpu_attn_backend.py to FastDeploy/fastdeploy/model_executor/layers/backends/xpu (#5878)

2026-01-09 16:34:57 +08:00