apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity
Files
4c911ecb742bcf67b438f45fa3a8a13c3313f865
FastDeploy/custom_ops/gpu_ops/speculate_decoding
History
freeliuzc 11398790d3
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
Details
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
Details
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
Details
CE Compile Job / Show Code Archive Output (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
Details
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Details
Deploy GitHub Pages / deploy (push) Has been cancelled
Details
[Speculative Decoding][MTP]Support attn mask offset (#4641) 
* [MTP]Merge support attn (#4591)

* support mask_offset in speculate decoding

* fix dummpy run output

* add unit test

* fix unit test import

* support attn_mask_offset in mtp mode

* add update_attn_mask op

* fix unit test && fix code-style
2025-11-03 10:08:01 +08:00
..
draft_model
support mtp in splitewise and scheduler_v1 mode (#4743)
2025-11-03 10:07:15 +08:00
ngram_match.cc
Sync v2.0 version of code to github repo
2025-06-29 23:29:37 +00:00
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_padding_offset.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_padding_offset.cu
[Executor]CUDAGraph support Speculate Decode (#3769)
2025-10-09 21:18:29 +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
rename speculate_token_penalty_multi_scores.cu (#3735)
2025-09-02 18:12:11 +08:00
speculate_limit_thinking_content_length_v1.cu
[BugFix] fix thinking bug (#4710)
2025-10-31 22:00:31 +08:00
speculate_limit_thinking_content_length_v2.cu
[BugFix] fix thinking bug (#4710)
2025-10-31 22:00:31 +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_save_output_with_topk.cc
[Feature] support mtp logprob (#4464)
2025-10-20 15:18:12 +08:00
speculate_save_output.cc
[MTP]support mtp chunk_prefill_v1 (#4366)
2025-10-15 13:21:32 +08:00
speculate_schedule_cache.cu
support mtp in splitewise and scheduler_v1 mode (#4743)
2025-11-03 10:07:15 +08:00
speculate_set_stop_value_multi_seqs.cu
rename speculate_stop_generation_multi_stop_seqs (#3743)
2025-09-02 18:04:29 +08:00
speculate_set_value_by_flags_and_idx.cu
Optimizing the performance of think length limit using custom operators (#4279)
2025-10-20 21:09:13 +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
[Speculative Decoding][MTP]Support attn mask offset (#4641)
2025-11-03 10:08:01 +08:00
speculate_verify.cu
[Feature] support mtp distribution equivalence verification (#4699)
2025-10-31 11:45:04 +08:00
top_p_candidates.cu
[MTP]support more branchs in topp kernel (#4352)
2025-10-11 11:33:52 +08:00