AndyLi429andAndyLi429 d903351a66 [NPU][bugfix] update low latency quantization input and update MXFP8 tests (#38831) ...

Co-authored-by: AndyLi429 <AndyLi429@noreply.gitcode.com>

2026-09-20 09:55:30 +08:00

..

attention

[NPU][DSV4]dsv4 enable cpp (#39820)

2026-09-20 09:17:27 +08:00

quantization

[NPU][bugfix] update low latency quantization input and update MXFP8 tests (#38831)

2026-09-20 09:55:30 +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