SoluMilken c95dc88f86 [CI] migrate ascend-gptq from test/srt to test/registered (#19628)

2026-03-14 00:28:57 -07:00

..

test_ascend_autoround_dense.py

[Feature][NPU]: add runtime support for AutoRound quantized models (#16699)

2026-03-07 18:03:55 +03:00

test_ascend_autoround_moe.py

[Feature][NPU]: add runtime support for AutoRound quantized models (#16699)

2026-03-07 18:03:55 +03:00

test_ascend_compile_graph_tp1_bf16.py

…

test_ascend_deepep.py

…

test_ascend_gptq_moe.py

[Feature][NPU]: add runtime support for GPTQ-quantized MoE models (#16364)

2026-03-04 16:02:19 +03:00

test_ascend_graph_tp1_bf16.py

…

test_ascend_graph_tp2_bf16.py

…

test_ascend_hicache_mha.py

…

test_ascend_hicache_mla.py

…

test_ascend_mla_fia_w8a8int8.py

…

test_ascend_mla_w8a8int8.py

…

test_ascend_piecewise_graph_prefill.py

Piecewise Cuda Graph set default (#16331)

2026-03-02 23:18:07 +08:00

test_ascend_sampling_backend.py

…

test_ascend_tp1_bf16.py

…

test_ascend_tp2_bf16.py

[NPU]Optimize the PR pipeline to reduce E2E runtime (#18767)

2026-02-28 17:06:03 +08:00

test_ascend_tp2_fia_bf16.py

…

test_ascend_tp4_bf16.py

…

test_ascend_w4a4_quantization.py

…

test_ascend_w8a8_quantization.py

…

test_llada2_mini_ascend.py

[NPU] [DLLM]DLLM LLaDA2.x graph mode support with NPU speedup modifications (#18485)

2026-03-09 22:41:05 +08:00