Liangsheng Yin bf90ea9c5b Unify spec v2's naming manner. (#15990)

2025-12-28 14:14:52 +08:00

..

test_ascend_compile_graph_tp1_bf16.py

[Feature] npu support enable_torch_compile for torchair backend (#13410)

2025-12-16 09:23:51 +08:00

test_ascend_deepep.py

[NPU][1/N] NPU basic functions refactor and new modelslim quant type (#13359)

2025-12-04 16:15:31 +08:00

test_ascend_deepseek_mtp.py

Unify spec v2's naming manner. (#15990)

2025-12-28 14:14:52 +08:00

test_ascend_graph_tp1_bf16.py

…

test_ascend_graph_tp2_bf16.py

…

test_ascend_hicache_mha.py

…

test_ascend_hicache_mla.py

[BugFix] fix prefixcache performance and accuracy on ascend (#13573)

2025-12-08 02:16:20 +08:00

test_ascend_mla_fia_w8a8int8.py

[NPU][1/N] NPU basic functions refactor and new modelslim quant type (#13359)

2025-12-04 16:15:31 +08:00

test_ascend_mla_w8a8int8.py

[NPU][1/N] NPU basic functions refactor and new modelslim quant type (#13359)

2025-12-04 16:15:31 +08:00

test_ascend_piecewise_graph_prefill.py

[Ascend]Support of piecewise graph compilation for prefill on NPU (#12287)

2025-12-11 21:10:07 +08:00

test_ascend_sampling_backend.py

…

test_ascend_tp1_bf16.py

…

test_ascend_tp2_bf16.py

…

test_ascend_tp2_fia_bf16.py

…

test_ascend_tp4_bf16.py

[NPU] adapt dsv3.2 nsa prefill context parallel (#14541)

2025-12-11 20:12:59 +08:00