109 Commits

Author	SHA1	Message	Date
kevin	8aab4e367f	[Feature] mm support prefix cache (#4134) ... * support mm prefix caching * update code * fix mm_hashes * support encoder cache * add encoder cache * update code * update encoder cache * fix features bug * fix worker bug * support processor cache, need to optimize yet * refactor multimodal data cache * update code * update code * update v1 scheduler * update code * update code * update codestyle * support turn off processor cache and encoder cache * update pre-commit * fix code * solve review * update code * update code * update test case * set processor cache in GiB * update test case * support mm prefix caching for qwen model * fix code style check * update pre-commit * fix unit test * fix unit test * add ci test case * fix rescheduled bug * change text_after_process to prompt_tokens * fix unit test * fix chat template * change model path * [EP] fix adapter bugs (#4572) * Update expert_service.py * Update common_engine.py * Update expert_service.py * fix v1 hang bug (#4573) * fix import image_ops error on some platforms (#4559) * [CLI]Update parameters in bench latecy cli tool and fix collect-env cli tool (#4558) * add collect-env * del files * [Graph Optimization] Add dy_runnable and introduce cudagraph_switch_threshold for cudagraph mode switching (#4578) * add new branch for sot * reorder * fix batch bug * [XPU]Moe uses a new operator (#4585) * [XPU]Moe uses a new operator * [XPU]Moe uses a new operator * update response * [Feature] Support Paddle-OCR (#4396) * init * update code * fix code style & disable thinking * adapt for common_engine.update_mm_requests_chunk_size * use 3d rope * use flash_attn_unpadded * opt siglip * update to be compatible with the latest codebase * fix typo * optim OCR performance * fix bug * fix bug * fix bug * fix bug * normlize name * modify xpu rope * revert logger * fix bug * fix bug * fix bug * support default_v1 * optim performance * fix bug --------- Co-authored-by: root <root@szzj-acg-tge1-fdda9.szzj.baidu.com> Co-authored-by: zhangyue66 <zhangyue66@baidu.com> * [DataProcessor] add reasoning_tokens into usage info (#4520) * add reasoning_tokens into usage info initial commit * add unit tests * modify unit test * modify and add unit tests * fix unit test * move steam usage to processor * modify processor * modify test_logprobs * modify test_logprobs.py * modify stream reasoning tokens accumulation * fix unit test * perf: Optimize task queue communication from engine to worker (#4531) * perf: Optimize task queue communication from engine to worker * perf: get_tasks to numpy * perf: get_tasks remove to_numpy * fix: request & replace ENV * remove test_e2w_perf.py * fix code style --------- Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com> * Clean up ports after processing results (#4587) * [CI] Add /re-run command in PR comments to restart failed CI workflows (#4593) * [Others] api server exits when worker process is dead (#3271) * [fix] fix terminal hangs when worker process is dead * [chore] change sleep time of monitor * [chore] remove redundant comments * update docs --------- Co-authored-by: ApplEOFDiscord <wwy640130@163.com> Co-authored-by: ApplEOFDiscord <31272106+ApplEOFDiscord@users.noreply.github.com> Co-authored-by: ltd0924 <32387785+ltd0924@users.noreply.github.com> Co-authored-by: yinwei <yinwei_hust@163.com> Co-authored-by: JYChen <zoooo0820@qq.com> Co-authored-by: qwes5s5 <45442318+qwes5s5@users.noreply.github.com> Co-authored-by: Ryan <zihaohuang@aliyun.com> Co-authored-by: yyssys <atyangshuang@foxmail.com> Co-authored-by: ming1753 <61511741+ming1753@users.noreply.github.com> Co-authored-by: root <root@szzj-acg-tge1-fdda9.szzj.baidu.com> Co-authored-by: zhangyue66 <zhangyue66@baidu.com> Co-authored-by: kxz2002 <115912648+kxz2002@users.noreply.github.com> Co-authored-by: SunLei <sunlei5788@gmail.com> Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com> Co-authored-by: Zhang Yulong <35552275+ZhangYulongg@users.noreply.github.com> Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com> Co-authored-by: 李泳桦 <39643373+liyonghua0910@users.noreply.github.com>	2025-10-27 17:39:51 +08:00
ming1753	e4e3cede7f	[Feature] Support Paddle-OCR (#4396) ... * init * update code * fix code style & disable thinking * adapt for common_engine.update_mm_requests_chunk_size * use 3d rope * use flash_attn_unpadded * opt siglip * update to be compatible with the latest codebase * fix typo * optim OCR performance * fix bug * fix bug * fix bug * fix bug * normlize name * modify xpu rope * revert logger * fix bug * fix bug * fix bug * support default_v1 * optim performance * fix bug --------- Co-authored-by: root <root@szzj-acg-tge1-fdda9.szzj.baidu.com> Co-authored-by: zhangyue66 <zhangyue66@baidu.com>	2025-10-24 23:34:30 +08:00
RAM	775edcc09a	[Executor] Default use CUDAGraph (#3594) ... * add start intercept * Adjustment GraphOptConfig * pre-commit * default use cudagraph * set default value * default use cuda graph * pre-commit * fix test case bug * disable rl * fix moba attention * only support gpu * Temporarily disable PD Disaggregation * set max_num_seqs of test case as 1 * set max_num_seqs and temperature * fix max_num_batched_tokens bug * close cuda graph * success run wint2 * profile run with max_num_batched_tokens * 1.add c++ memchecker 2.success run wint2 * updatee a800 yaml * update docs * 1. delete check 2. fix plas attn test case * default use use_unique_memory_pool * add try-except for warmup * ban mtp, mm, rl * fix test case mock * fix ci bug * fix form_model_get_output_topp0 bug * fix ci bug * refine deepseek ci * refine code * Disable PD * fix sot yaml	2025-10-21 14:25:45 +08:00
Yuanle Liu	cef3164c3b	Optimizing the performance of think length limit using custom operators (#4279) ... * delete impl * delete min_length&max_length * support limit thinking content strategy * fix * fix * fix * update * fix set_value_by_flags_and_idx * fix * fix * fix * fix * update * fix * fix * fix typo * fix ci * fix * fix * support mtp * fix * fix * update * update	2025-10-20 21:09:13 +08:00
GoldPancake	47595a2480	[Feature] support mtp logprob (#4464) ... * support mtp logprob * fix unitest	2025-10-20 15:18:12 +08:00
RAM	528c55776e	[Graph Optimization][Speculative Decoding] Fix the bug of CUDAGraph + MTP + EP (#4456) ... * Fix MTP dummy run bug * Target Model and Draft Model using the same flag * In mtp replace use_cudagraph as step_use_cudagraph	2025-10-20 10:38:55 +08:00
yzwu	4b661512ca	[Iluvatar GPU] Adapt VL model (#4313)	2025-10-17 16:13:38 +08:00
lizexu123	c234b995ab	[Feature] support pooling model dummy_run (#4345) ... * support qwen3-embedding * fix ci bug * support pooling dummy_run * fix * delete print * parallel_config.max_model_len * delete is_pooling_model in dummy_run * fix * fd_model * fix embedding load * fix * fix post_process	2025-10-17 13:30:55 +08:00
chenjian	0413c32b8f	[Optimize] Set preempted schedule log as info level (#4453)	2025-10-17 11:25:46 +08:00
YuanRisheng	a37c9416ac	[FDConfig]Remove reasoning_parser/guided_decoding_backend/disable_any_whitespace/device_ids in FDConfig (#4362) ... * remove devices id * fix unittest * fix ce --------- Co-authored-by: root <root@yqlcc01-sys-rpm12rzmwjd.yqlcc01.baidu.com>	2025-10-17 10:40:59 +08:00
YuanRisheng	0355235fb9	[FDConfig]Remove total_block_num/dtype/block_size/enc_dec_block_num in ParallelConfig (#4400) ... * delete some attr in parallel config * delete comment --------- Co-authored-by: root <root@yqlcc01-sys-rpm12rzmwjd.yqlcc01.baidu.com>	2025-10-16 20:00:37 +08:00
Ryan	b87e2c6184	[CUDAGraph]Add support for custom all-reduce operators under SOT mode (#4386)	2025-10-16 19:31:19 +08:00
SunLei	5abf59715d	perf: optimize ZMQ communication with async queue and single-threaded… (#4444) ... * perf: optimize ZMQ communication with async queue and single-threaded model * perf: _async_output_busy_loop * fix: async_output_queue init	2025-10-16 15:46:26 +08:00
freeliuzc	582aebd48b	[MTP]support mtp chunk_prefill_v1 (#4366) ... * support mtp chunk_prefill_v1 * fix mtp chunkprefill output, fix unit test * fix unit test * fix save_output	2025-10-15 13:21:32 +08:00
Sunny-bot1	a751d977bc	[Optimization] Fuse get_max_len and get_kv_max_len (#4369) ... * opt split_q_block * fuse max_lens and max kv_len	2025-10-13 20:35:00 +08:00
YuanRisheng	a2ec2c4152	[FDConfig]Remove max_model_len in FDConfig (#4350) ... * modify max_model_len * fix unittest * fix unittest --------- Co-authored-by: root <root@yqlcc01-sys-rpm12rzmwjd.yqlcc01.baidu.com>	2025-10-11 14:04:17 +08:00
ltd0924	3f535b45a2	[Feature] support prefix cache in DP (#4359) ... * [Feature] support prefix cache in DP * fix * Update common_engine.py * Update common_engine.py * Update common_engine.py * Update common_engine.py --------- Co-authored-by: ltd0924 <luotingdan@baidu.com>	2025-10-11 10:12:12 +08:00
RAM	aa27b03bc0	[Executor]CUDAGraph support Speculate Decode (#3769) ... * success run ngram * Revert "[Code Simplification] remove cum_offsets (#3410)" This reverts commit 32b39620bc. * success run ngram5 tp4 42bs * success run ngram5 tp4 42bs * mtp draft commit * add decorator for target model * enable draft model in cudagraph v0.5 * revert revrt cum_offset * enable target model in cudagraph v0.9 And clean debug code * Revert "success run ngram" This reverts commit 8351e83993. * add reverted code * enable target model in cudagraph v0.9 * solve comment * fix bid < 0 * Enable Target Model Padding And Draft Model in cudagraph * solve problem * delete rebuild padding debug note * fast compile * Add capture list for mtp * success run 256 tp1 mtp * Enable Lite TP2 Bsz256 * realy enable tp2 bsz 256 * fix problem * Solve problem for Draft model in cudagraph * Solve comment * replace emptytensor as zeros * Solve comments * Revert "fast compile" This reverts commit 834639a7ff. * fix bug * fix merge bug * fix typo * fix bug --------- Co-authored-by: lizexu <2694294196@qq.com> Co-authored-by: littledgg <1658565283@qq.com> Co-authored-by: zeroRains <linjunlu@zerorains.top> Co-authored-by: gongshaotian <gstain5555@outlook.com>	2025-10-09 21:18:29 +08:00
AIbin	48fd5d757d	Support MLA_CACHE & Fix V1_Schedule Bug (#4318) ... Support MLA_CACHE & Fix V1_Schedule Bug	2025-10-09 12:11:25 +08:00
李泳桦	6265f4385f	[feat] support prefix cache clearing when /clear_load_weight is called (#4008) ... * [feat] support clearing prefix cache (cherry-picked from release/2.1) * [fix] fix ipc suffix, use port instead * [fix] fix prefix caching not enabled * [fix] fix key/value_cache_scales indent * [fix] fix ep group all-reduce * [fix] fix clear/update lock not working when workers > 1 * [chore] add preemption triggered info log * [fix] fix code style * [fix] fix max_num_seqs config * [fix] do not force enable_prefix_caching=False in dynamic loading * [fix] fix ci * Revert "[fix] fix ci" This reverts commit 0bc6d55cc8. * [fix] initialize available_gpu_block_num with max_gpu_block_num * [fix] fix config splitwise_role * [fix] fix clearing caches synchronization and add more logs * [chore] print cache_ready_signal in log * [fix] fix scheduler_config.splitwise_role * [fix] fix cache_messager cache_ready_signal create=True * [fix] stop cache messager from launching in mixed deployment	2025-09-28 19:42:53 +08:00
K11OntheBoat	4515ad21e9	Support limit thinking lengths (#4069) ... Co-authored-by: K11OntheBoat <“ruianmaidanglao@163.com”>	2025-09-25 19:55:56 +08:00
lizexu123	e8318b7477	[BugFix] fix qwen3-embedding model tp>1 (#4223) ... * support qwen3-embedding * fix ci bug * fix * fix ci bug * fix ci bug * fix * fix qwen3-embedding * fix * fix * fix	2025-09-24 14:13:26 +08:00
ltd0924	83720da79f	[Feature] support clear data (#3601) ... * [Feature] support clear data * update * fix * fix * fix * fix * fix * fix * fix	2025-09-23 10:20:02 +08:00
lizexu123	c86945ef49	[Feature] support pool (#3827) ... * support pool * update pooling * add pooler_config and check * update * support AutoWeightsLoader load weight * fix * update * delete print * update pre-commit * fix * fix xpu * fix ModelRegistry->model_registry * fix Copilot review * fix pooler.py * delete StepPooler * fix abstract * fix default_loader_v1 * fix Pre Commit * support torch qwen3 dense * add test and fix torch-qwen * fix * fix * adapter ci: * fix review * fix pooling_params.py * fix * fix tasks.py 2025 * fix print and logger * Modefy ModelRegistry and delete AutoWeightsLoader * fix logger * fix test_embedding * fix ci bug * ernie4_5 model_registry * fix test * support Qwen3-Embedding-0.6B tp=1 load * fix extra code * fix * delete fix vocab_size * delete prepare_params_dict * fix:	2025-09-22 14:09:09 +08:00
YuanRisheng	24180fba0a	[FDConfig]Remove splitwise_role and engine_worker_queue_port in FDConfig (#4147) ... * remove splitwise_role and engine_worker_queue_port * fix xpu * fix xpu * fix xpu * fix unittest * resolve conflct	2025-09-19 17:01:52 +08:00
chenjian	618ccdbfba	[Feature] Support mixed deployment with yiyan adapter in develop (#3976) ... * [Feature] Support mixed deployment with yiyan adapter in release2.2 * fix metrics * add unit test * add unit test * add unit test * fix ci * fix for eb5 * fix ci * fix ci * fix ci --------- Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com> Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>	2025-09-18 01:52:20 +08:00
RichardWooSJTU	2adca04f1f	Reconstruct streaming data transfer with zmq (#3836) ... * reconstruct USE_GET_SAVE_OUTPUT_V1 * fix ut * use dp rank * fix ci	2025-09-17 14:30:39 +08:00
YuanRisheng	2e9e53ff7e	[FDConfig]Remove max_num_batched_tokens/max_num_seqs in parallel config (#4116) ... * remove max_num_batched_tokens in parallel config * remove max_num_seqs * update test case * fix test * fix --------- Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>	2025-09-17 10:43:35 +08:00
xiaoxiaohehe001	abdcef30aa	[BugFix] mm_post_fix (#4005) ... * mm_post_fix * mm_post_fix_1	2025-09-11 19:09:46 +08:00
AIbin	a7392a0ff9	【Inference Optimize】DeepSeek-V3-model MLA Optimize (#3886) ... * support MLA chunk_size auto search & cuda_graph	2025-09-11 10:46:09 +08:00
chen	637d96c6ae	[Feature] Support zai-org/GLM-4.5-Air BF16 model (#3928) ... * support glm45_air	2025-09-10 19:36:10 +08:00
RAM	d3e4ae3d49	[Executor] Adjust signal sending order in RL training (#3773) ... * Adjust processing order * fix bug * fix update_parameters bug * refine code	2025-09-10 13:24:20 +08:00
Jundong Liu	3d0aaa5923	[Excutor] Experiment Feature-Support Prefill in cudagraph (#3459) ... * Support prefill in Cudagraph * Refactor GetBlockShapeAndSplitKVBlock Kernel V2 * Refactor GetBlockShapeAndSplitKVBlock Kernel V2.1 * Refactor GetBlockShapeAndSplitKVBlock Kernel V2.2 * Refactor GetBlockShapeAndSplitKVBlock Kernel V2.3 * Refactor GetBlockShapeAndSplitKVBlock Kernel V2.4 * Refactor GetBlockShapeAndSplitKVBlock Kernel V2.5 * Solve problem about encoder_num_blocks_x_cpu * Add early-exit mechanism for attention kernel * fix test case about append-attention * Update testcode, Add annotations to related tensors * move get_input_length_list * solve test_code * Add annotations about early-exit for attention kernel * Add annotations about early-exit for attention kernel2 * solve comment * solve mtp --------- Co-authored-by: RAM <gstian5555@outlook.com>	2025-09-08 13:12:24 +08:00
lzy	af49b81ffd	supports dynamic Cfp8 (#3767) ... * supports dynamic Cfp8 * add unittest	2025-09-07 20:41:29 -07:00
chenjian	b5e20e3015	[Bug fix] Fix prompt token ids dtype in v1 (#3860)	2025-09-08 11:34:13 +08:00
freeliuzc	88d44a2c93	support mtp in v1_scheduler mode (#3695)	2025-09-04 17:39:59 +08:00
chenjian	22c165d6dd	[Feature] Set v1 scheduler as default in develop (#3807) ... * Set scheduler v1 as default * Set scheduler v1 as default * Set scheduler v1 as default * Set scheduler v1 as default * Set scheduler v1 as default * close V1 in guided_decoding * fix vl ci * close V1 in guided_decoding	2025-09-04 15:16:56 +08:00
Longzhi Wang	e0c9a6c76c	[Feat] Support streaming transfer data using ZMQ (#3521) ... * Support streaming transfer data of ZMQ * fix typo * fix typo * support tp * add unittest * update * update * fix typo * fix typo * fix tp_num in ci machine --------- Co-authored-by: Wanglongzhi2001 <>	2025-09-02 19:52:19 +08:00
kevin	1908465542	[Feature] mm and thinking model support structred output (#2749) ... * mm support structured output * update code * update code * update format * update code * update code * add enable_thinking default * update code * add structured_outputs test case * add ci install xgrammar * add ci timeout time * update test for structured_outputs * update code * add error traceback info * update error msg * update structred output code * update code * update code * update config * update torch version --------- Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>	2025-09-02 16:21:09 +08:00
zhouchong	ccd52b5596	[Model]support qwen2_5_vl (#3557) ... * adapt qwen_2_5_vl model * adapt qwen_2_5_vl VIT model * adapt qwen2_5_vl images_embeds * adapt qwen2_5_vl 3D rope * adapt qwen2_5_vl 3D rope v2 * adapt qwen2_5_vl processor * adapt qwen2_5_vl bypass resampler_model * adapt qwen2_5_vl 绕过部分ernie逻辑 * adapt qwen2_5_vl 绕过部分ernie逻辑 v2 * adapt qwen2_5_vl 权重加载与命名修改 * adapt qwen2_5_vl 非必须think_end_id * adapt qwen2_5_vl 区分多种模型的extract_vision_features * fix:adapt qwen2_5_vl model * adapt qwen2_5_vl norm * adapt qwen2_5_vl processor 更新 * adapt qwen2_5_vl image and video success * adapt qwen2_5_vl 部分整理代码 * adapt qwen2_5_vl 支持多卡 * adapt qwen2_5_vl on latest develop * adapt qwen2_5_vl RL * adapt qwen2_5_vl 整理代码 * support noex rope3d * adapt qwen2_5_vl add init.py * adapt qwen2_5_vl add init.py v2 * adapt qwen2_5_vl remove space * adapt qwen2_5_vl remove space v2 * adapt qwen2_5_vl pre-commit * adapt qwen2_5_vl update * adapt qwen2_5_vl pre-commit v2 * adapt qwen2_5_vl modify comments * adapt qwen2_5_vl fix indentation * adapt qwen2_5_vl fix indentation v2 --------- Co-authored-by: wangyafeng <wangyafeng@baidu.com> Co-authored-by: xiaoxiaohehe001 <49090790+xiaoxiaohehe001@users.noreply.github.com> Co-authored-by: CSWYF3634076 <58356743+CSWYF3634076@users.noreply.github.com>	2025-08-29 18:28:39 +08:00
lifulll	72094d4d82	enable dcu ci (#3402)	2025-08-29 10:23:08 +08:00
Zero Rains	e37e86b3b8	[V1 Loader]support param create and load for wint2 and xpu backend (#3581) ... * support wint2 backend' * [V1 Loader]support param create and load for wint2 and xpu backend * update weight shape name * update * update * update baseline.txt * update model name * update baseline.txt * fix codestyle * remove debug coode	2025-08-28 09:49:36 +08:00
lizexu123	b28a0343a6	fix ENABLE_V1_KVCACHE_SCHEDULER (#3625) ... Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>	2025-08-27 21:21:29 +08:00
李泳桦	b2afdf4fc6	[fix] qwen output inconsistency when top_p=0 (#3634) ... * [fix] qwen output inconsistency when top_p=0 * [fix] remove decode pre_id code	2025-08-27 17:16:23 +08:00
gaoziyuan	82e64b13e1	[NewFeature]Support dp multi api server && Fix some bug in mixed ep && merge develop (#3598) ... * [Feature] update ep * fix ci * fix ci * fix ci * fix ci * fix ci * fix ci * fix ci * fix queue ports idx * fix ci * fix ci * fix ci * fix ci * fix ci * fix ci * fix ci * fix ci * Update engine.py * fix ci * fix some bug in mixed ep * add server fix and op fix * rm some log * fix code style * ltd fix * fix * fix * fix some bug * fix bug * fix bug * fix style * Update config.py * Update splitwise_connector.py * Update cache_messager.py * Update __init__.py * merge and fix * Update engine.py * Update common_engine.py * Update run_ci_xpu.sh * Update ernie_processor.py * Update ernie_processor.py --------- Co-authored-by: ltd0924 <ltd0924@sina.com> Co-authored-by: ltd0924 <32387785+ltd0924@users.noreply.github.com>	2025-08-26 19:59:02 +08:00
Yuanle Liu	cbce94a00e	rename ernie_xxx to ernie4_5_xxx (#3621) ... * rename ernie_xxx to ernie4_5_xxx * ci fix	2025-08-26 19:29:27 +08:00
lzy	d339df2e90	Supports DP+TP+EP hybrid parallel deployment strategy (#3489) ... * Support DP+TP+EP hybrid parallel deployment strategy * Support DP+TP+EP hybrid parallel deployment strategy * fix conflict * add moe_tp_ep function split_allgather_out * del tp_group in moe_cutlass_backend * for ci * fix parallel_config for ci * del log	2025-08-26 00:04:01 -07:00
Sunny-bot1	c68c3c4b8b	[Feature] bad words support v1 scheduler and specifiy token ids (#3608) ... * support bad_words_token_ids * docs * fix test * fix * bad words support kvcache v1 and token ids * fix	2025-08-25 20:14:51 -07:00
RAM	2fa173e327	[Executor] CUDAGraph support RL training (#3265) ... * add clear graph opt backend * cuda graph support rl * add branch * 1.fix dynamic_weight_manager bug 2.add clear api for CasualLM * open test case * fix typo * update mkdocs.yaml * [Docs]Update mkdocs.yml * update test case * use unittest in graph test case	2025-08-25 20:59:30 +08:00
chen	9cab3f47ff	[Feature] Add temp_scaled_logprobs and top_p_normalized_logprobs parameters for logits and logprobs post processing (#3552) ... * [feature] Add temp_scaled_logprobs and top_p_normalized_logprobs parameters for logits and logprobs post processing * infer engine support temp_scaled_logprobs and top_p_normalized_logprobs * delete some code * code check * code check and add doc * fix tokenizer.decoder(-1), return 'Invalid Token' * add ci for temp_scaled and top_p logprobs * check test * check seq len time shape * logprob clip inf --------- Co-authored-by: sunlei1024 <sunlei5788@gmail.com>	2025-08-25 14:11:49 +08:00