freeliuzc 76759108c9 [Feature][SpeculativeDecoding]Support tree-attention (#3514) ...

* support tree-attention

* fix merge bug

* fix unit-test api

* fix merge bug

2025-08-22 13:36:41 +08:00

..

test_air_top_p_sampling.py

Add stable ci (#3460)

2025-08-20 08:57:17 +08:00

test_cutlass_scaled_mm.py

Add stable ci (#3460)

2025-08-20 08:57:17 +08:00

test_deqant_int8_cpp_extension.py

Add stable ci (#3460)

2025-08-20 08:57:17 +08:00

test_dequant.py

Add stable ci (#3460)

2025-08-20 08:57:17 +08:00

test_flash_mask_attn.py

Add stable ci (#3460)

2025-08-20 08:57:17 +08:00

test_fp8_fp8_half_cuda_core_gemm.py

Add stable ci (#3460)

2025-08-20 08:57:17 +08:00

test_fused_moe.py

Add stable ci (#3460)

2025-08-20 08:57:17 +08:00

test_get_token_penalty_multi_scores.py

Add stable ci (#3460)

2025-08-20 08:57:17 +08:00

test_moe_top_k_select.py

Add stable ci (#3460)

2025-08-20 08:57:17 +08:00

test_noaux_tc.py

Add stable ci (#3460)

2025-08-20 08:57:17 +08:00

test_perchannel_gemm.py

Add stable ci (#3460)

2025-08-20 08:57:17 +08:00

test_rejection_top_p_sampling.py

Add stable ci (#3460)

2025-08-20 08:57:17 +08:00

test_scaled_gemm_f8_i4_f16.py

Add stable ci (#3460)

2025-08-20 08:57:17 +08:00

test_split_fuse.py

Add stable ci (#3460)

2025-08-20 08:57:17 +08:00

test_stop_generation_multi_ends.py

Add stable ci (#3460)

2025-08-20 08:57:17 +08:00

test_token_penalty.py

Add stable ci (#3460)

2025-08-20 08:57:17 +08:00

test_tree_mask.py

[Feature][SpeculativeDecoding]Support tree-attention (#3514)

2025-08-22 13:36:41 +08:00

test_w4afp8_gemm.py

【bug fix】修复w4a8编译慢 (#3510)

2025-08-21 18:50:14 +08:00

test_wfp8afp8_sparse_gemm.py

Add stable ci (#3460)

2025-08-20 08:57:17 +08:00