Copilot e38709b499 [BugFix] Fix limit_thinking early return logic in CUDA kernels (#5471) ...

* Initial plan

* [BugFix] Fix limit_thinking bug - change AND to OR in condition checks

Co-authored-by: yuanlehome <23653004+yuanlehome@users.noreply.github.com>

* Update Chinese comments to reflect OR logic instead of AND

Co-authored-by: yuanlehome <23653004+yuanlehome@users.noreply.github.com>

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: yuanlehome <23653004+yuanlehome@users.noreply.github.com>

2025-12-10 11:03:19 +08:00

..

draft_model

…

ngram_match.cc

…

speculate_calcu_accept_ratio.cu

…

speculate_clear_accept_nums.cu

…

speculate_get_output_padding_offset.cu

…

speculate_get_output_with_topk.cc

…

speculate_get_output.cc

…

speculate_get_padding_offset.cu

Remove CUDA ERROR 9 of inputs of get_padding_offset kernel (#5440)

2025-12-09 14:17:30 +08:00

speculate_get_seq_lens_output.cu

…

speculate_get_token_penalty_multi_scores.cu

…

speculate_limit_thinking_content_length_v1.cu

[BugFix] Fix limit_thinking early return logic in CUDA kernels (#5471)

2025-12-10 11:03:19 +08:00

speculate_limit_thinking_content_length_v2.cu

[BugFix] Fix limit_thinking early return logic in CUDA kernels (#5471)

2025-12-10 11:03:19 +08:00

speculate_logprob_utils.cu

…

speculate_msg.h

…

speculate_save_output_with_topk.cc

…

speculate_save_output.cc

…

speculate_schedule_cache.cu

…

speculate_set_stop_value_multi_seqs.cu

[Feature] support stop_token_ids (#5399)

2025-12-09 17:49:12 +08:00

speculate_set_value_by_flags_and_idx.cu

…

speculate_step_reschedule.cu

…

speculate_step_system_cache.cu

…

speculate_step.cu

…

speculate_update_input_ids_cpu.cc

…

speculate_update.cu

…

speculate_verify.cu

…

top_p_candidates.cu

[Metax] modify wrapSize to WARP_SIZE (#5442)

2025-12-09 01:44:02 -08:00