huicongyao 0f718baaf2 [Speculative Decoding]Reformat input preprocess for spec decode (#6501) ...

* add speculate_pre_process kernel

* reduce one slice

* make d2h async && fix mtp bug for new pre_process

* fix

* add unitest

* fix: code stype formatting

* fix

* fix: thread race in speculate_preprocess && rename d2h event

2026-03-03 10:22:07 +08:00

..

draft_model

[MTP] refactor MTP pre_process (#6358)

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

ngram_match.cc

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

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

speculate_calcu_accept_ratio.cu

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

speculate_clear_accept_nums.cu

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

speculate_get_output_with_topk.cc

[Feature] support mtp logprob (#4464)

2025-10-20 15:18:12 +08:00

speculate_get_output.cc

[Feature][MTP]support new speculative decoding method named hybrid mtp with ngram (#3610)

2025-08-26 14:29:22 +08:00

speculate_get_seq_lens_output.cu

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

speculate_get_token_penalty_multi_scores.cu

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

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

speculate_limit_thinking_content_length.cu

[OP][Feature] 统一 limit_thinking_content_length CUDA 算子，支持回复长度限制与注入序列 (#6493)

2026-02-25 21:36:50 +08:00

speculate_logprob_utils.cu

[Feature] support mtp logprob (#4464)

2025-10-20 15:18:12 +08:00

speculate_msg.h

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

speculate_preprocess.cu

[Speculative Decoding]Reformat input preprocess for spec decode (#6501)

2026-03-03 10:22:07 +08:00

speculate_save_output_with_topk.cc

[Optim] Robust sync status when preempted happens (#5796)

2026-01-14 12:07:33 +08:00

speculate_save_output.cc

[Optim] Robust sync status when preempted happens (#5796)

2026-01-14 12:07:33 +08:00

speculate_schedule_cache.cu

[Others] remove stop_nums (#6182)

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

speculate_set_stop_value_multi_seqs.cu

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

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

speculate_set_value_by_flags_and_idx.cu

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

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

speculate_step_reschedule.cu

fix typos (#3684)

2025-09-01 17:50:17 +08:00

speculate_step_system_cache.cu

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

speculate_step.cu

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

speculate_update_input_ids_cpu.cc

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

speculate_update.cu

[XPU] Fix PD + MTP (#6495)

2026-02-27 19:07:35 +08:00

speculate_verify.cu

[MTP] refactor MTP pre_process (#6358)

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

top_p_candidates.cu

[MTP] refactor MTP pre_process (#6358)

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