3 people e970453b43 [NPU]Refactor weight processing and add NPUSwigluLimit activation (#38420) ...

Co-authored-by: AndyLi429 <AndyLi429@noreply.gitcode.com>
Co-authored-by: Even Zhou <even.y.zhou@outlook.com>

2026-09-17 16:40:32 +08:00

..

attention

[NPU] Add NPU arch35 support and enhance DSV4 processing in DeepSeek-V4 (#37373)

2026-09-07 21:08:06 +08:00

quantization

[NPU]Refactor weight processing and add NPUSwigluLimit activation (#38420)

2026-09-17 16:40:32 +08:00

test_npu_arch35_capability.py

[NPU] Add NPU arch35 support and enhance DSV4 processing in DeepSeek-V4 (#37373)

2026-09-07 21:08:06 +08:00

test_sparsity_driven_kv_offload_config.py

[NPU] Add sparsity-driven KV offload for DeepSeek DSA on Ascend (#33089)

2026-09-09 09:13:22 +08:00