FastDeploy

test_air_top_p_sampling.py

Add stable ci (#3460 )

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

test_build_sampling_params.py

[Optimization][Speculative Decoding]Fuse padding sampling params (#6765 )

2026-03-12 05:05:15 -07:00

test_cutlass_fp8_fp8_fp8_dual_gemm_fused.py

【Hackathon 9th No.28】add test_cutlass_fp8_fp8_fp8_dual_gemm_fused (#3935 )

2025-09-10 14:57:49 +08:00

test_cutlass_scaled_mm.py

fix typos (#3633 )

2025-08-28 14:42:24 +08:00

test_depermute_prefill_combine.py

[Feature] Support EP prefill with num_worst_tokens (#6574 )

2026-03-11 17:09:07 +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_draft_model_postprocess.py

【Hackathon 9th No.63】add test_draft_model_postprocess.py (#3757 )

2025-09-04 15:00:48 +08:00

test_draft_model_preprocess.py

[Feature] Support mtp overlap schedule (#7001 )

2026-04-01 14:24:26 +08:00

test_draft_model_set_value_by_flags.py

[MTP] add test_draft_model_set_value_by_flags.py (#3741 )

2025-09-02 19:33:33 +08:00

test_draft_model_update.py

[Feature] Support mtp overlap schedule (#7001 )

2026-04-01 14:24:26 +08:00

test_dsmla_writecache.py

Dsa clean code，add dsk_attn_write_cache baseline (#6855 )

2026-03-16 11:01:14 +08:00

test_dynamic_per_token_scaled_fp8_quant.py

[Docs] Add License in Unittest (#4957 )

2025-11-12 10:44:09 +08:00

test_eagle_gather_hidden_states.py

[Speculative Decoding] Refactor Eagle MTP hidden states copy (#6812 )

2026-03-25 22:54:31 -07:00

test_eagle_get_hidden_states.py

[Speculative Decoding] Refactor Eagle MTP hidden states copy (#6812 )

2026-03-25 22:54:31 -07:00

test_eagle_get_self_hidden_states.py

[Speculative Decoding] Refactor Eagle MTP hidden states copy (#6812 )

2026-03-25 22:54:31 -07:00

test_flash_mask_attn.py

[Feature] Support cute cpp Encoder FA4 (#7016 )

2026-03-30 10:54:56 +08:00

test_fp8_fp8_half_cuda_core_gemm.py

Add stable ci (#3460 )

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

test_fused_get_rotary_embedding.py

【Hackathon 9th No.25】add test_fused_get_rotary_embedding (#3892 )

2025-09-12 15:38:43 +08:00

test_fused_hadamard_quant_fp8.py

[Docs] Add License in Unittest (#4957 )

2025-11-12 10:44:09 +08:00

test_fused_masked_swiglu_quant.py

[Optimize] optimize mask_quant & swiglu (#6222 )

2026-02-02 13:52:38 +08:00

test_fused_moe.py

[BugFix] fix wint2 (#6109 )

2026-01-20 21:46:21 +08:00

test_fused_neox_rope_embedding.py

[Feature] Optim PaddleOCR-VL (#4873 )

2025-11-07 14:56:44 +08:00

test_fused_rotary_position_encoding.py

[Optimization] [OP] [Models] dsk del prefill mask (#7313 )

2026-04-11 19:32:27 +08:00

test_gelu_tanh.py

[Feature] Optim PaddleOCR-VL (#4873 )

2025-11-07 14:56:44 +08:00

test_get_padding_offset.py

remove speculate_get_padding_offset op (#6308 )

2026-02-03 15:18:12 +08:00

test_get_position_ids_and_mask_encoder_batch.py

[Optimization][DeepSeekV3.2]Reducing slot_mapping compute frequency from twice per layer to a single pre-processing step. (#7367 )

2026-04-16 19:54:12 +08:00

test_get_token_penalty_multi_scores.py

[Feature] GPU Memory Optimization and Retirement of V0 Scheduler (#6407 )

2026-02-28 15:07:43 +08:00

test_group_swiglu_with_masked.py

【Hackathon 9th No.32】add unit tests for group_swiglu_with_masked (#3748 )

2025-09-05 11:53:47 +08:00

test_hybrid_mtp_ngram.py

[Docs] Add License in Unittest (#4957 )

2025-11-12 10:44:09 +08:00

test_machete_mm.py

[Optimize] Machete using group scale default (#4121 )

2025-09-18 13:51:11 +08:00

test_moe_redundant_topk_select.py

【Hackathon 9th No.35】add test_moe_redundant_topk_select (#3867 )

2025-09-05 11:29:02 +08:00

test_moe_top_k_select.py

Add stable ci (#3460 )

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

test_naive_update_model_status.py

[Speculative Decoding] refactor MTP and optimize spec-decoding postprocess (#6973 )

2026-03-24 10:19:01 +08:00

test_ngram_match.py

[Feature] GPU Memory Optimization and Retirement of V0 Scheduler (#6407 )

2026-02-28 15:07:43 +08:00

test_noaux_tc_redundant.py

[RL] support moe-topk use topk_reduce_func (#7218 )

2026-04-09 11:01:03 +08:00

test_noaux_tc.py

[Docs] Add License in Unittest (#4957 )

2025-11-12 10:44:09 +08:00

test_per_token_quant.py

[Feature] Support EP prefill with num_worst_tokens (#6574 )

2026-03-11 17:09:07 +08:00

test_permute_prefill_masked_gemm.py

[BugFix] Fix ep compatibility issues & Optimize permute operator (#6821 )

2026-03-17 10:32:11 +08:00

test_pre_cache_len_concat.py

[Others] Remove useless code (#5404 )

2025-12-08 13:59:46 +08:00

test_qk_rmsnorm_fused.py

[Optimization] Support FA2/FA3/FA4 with attn_mask_q (#6354 )

2026-02-05 14:39:00 +08:00

test_radix_topk_accuracy.py

fix dsa (#7252 )

2026-04-08 20:21:38 +08:00

test_reasoning_phase_token_constraint.py

[Speculate Decoding] Fix bug of reasoning_phase_token_constraint kernel (#7349 )

2026-04-14 20:57:11 +08:00

test_rebuild_padding.py

[MTP] refactor MTP pre_process (#6358 )

2026-02-09 10:47:15 +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_set_value_by_flags_and_idx.py

[Feature] GPU Memory Optimization and Retirement of V0 Scheduler (#6407 )

2026-02-28 15:07:43 +08:00

test_share_external_data.py

【Hackathon 9th No.22】add unit tests for share_external_data (#3744 )

2025-09-08 17:05:48 +08:00

test_speculate_get_seq_lens_output.py

[UnitTest][MTP]add test_speculate_get_padding_offset (#3730 )

2025-09-03 22:21:02 +08:00

test_speculate_get_target_logits.py

Add ut for speculative sampler (#4650 )

2025-10-30 10:37:49 +08:00

test_speculate_get_token_penalty_multi_scores.py

[Speculative Decoding][BugFix] Fix apply repeat times penalty kernel and change spec default verify strategy (#7467 )

2026-04-18 00:38:01 +08:00

test_speculate_insert_first_token.py

Add ut for speculative sampler (#4650 )

2025-10-30 10:37:49 +08:00

test_speculate_pre_process.py

[Optimization][Speculative Decoding]Fuse padding sampling params (#6765 )

2026-03-12 05:05:15 -07:00

test_speculate_set_stop_value_multi_seqs.py

[Speculate Decoding] Fix step_idx semantics in limit_thinking and set_stop_value kernels (#7166 )

2026-04-13 20:53:42 +08:00

test_speculate_update.py

[Others] remove stop_nums (#6182 )

2026-01-26 12:12:47 +08:00

test_speculate_verify.py

[MTP] refactor MTP pre_process (#6358 )

2026-02-09 10:47:15 +08:00

test_speculative_schedule_cache.py

[Feature] Support mtp overlap schedule (#7001 )

2026-04-01 14:24:26 +08:00

test_split_fuse.py

[CI] Standard unittest (#3606 )

2025-08-26 19:03:11 +08:00

test_stop_generation_multi_ends.py

[Feature] GPU Memory Optimization and Retirement of V0 Scheduler (#6407 )

2026-02-28 15:07:43 +08:00

test_swap_layout.py

[CI] Add unit test for swap_layout && remove unit test of splitwise_scheduler (#6250 )

2026-01-28 19:20:20 +08:00

test_token_penalty.py

[CI] Standard unittest (#3606 )

2025-08-26 19:03:11 +08:00

test_top_k_renorm_probs.py

【Hackathon 9th No.37】add test_top_k_renorm_probs (#3755 )

2025-09-16 11:12:46 +08:00

test_top_p_candidates.py

[Docs] Add License in Unittest (#4957 )

2025-11-12 10:44:09 +08:00

test_tree_mask.py

add more cases for attention unit test (#5931 )

2026-01-15 19:52:35 +08:00

test_tritonmoe_preprocess.py

【Hackathon 9th No.30】add test_tritonmoe_preprocess (#3891 )

2025-09-22 15:31:32 +08:00

test_unified_update_model_status.py

[Speculate Decoding] Fix step_idx semantics in limit_thinking and set_stop_value kernels (#7166 )

2026-04-13 20:53:42 +08:00

test_update_attn_mask.py

[Speculative Decoding] Optimize attn_mask_offset and fix mtp bug (#7005 )

2026-03-25 01:52:06 -07:00

test_update_inputs_v1.py

[Model Runner] Refactor execute_model for GPU async scheduling (#6176 )

2026-01-28 14:19:33 +08:00

test_verify_draft_tokens.py

[Speculative Decoding] Optimize attn_mask_offset and fix mtp bug (#7005 )

2026-03-25 01:52:06 -07:00

test_w4afp8_gemm.py

fix w4afp8 (#5634 )

2025-12-22 13:39:41 +08:00

test_wfp8afp8_sparse_gemm.py

fix typos (#3633 )

2025-08-28 14:42:24 +08:00