205 Commits

Author	SHA1	Message	Date
chenjian	db5d421aa3	[Optimize] Improve perf for fd response token with internal adapter (#4991) ... * [Optimize] Improve perf for fd response token with internal adapter * fix	2025-11-13 16:19:48 +08:00
chenjian	0d7f29841d	[Cherry-pick] Fix bug in develop for eb5 (#4845) ... * fix bug for PD EP * fix * optimize perf for engine worker queue * fix bug * fix internode ll two stage * fix for ci	2025-11-06 14:01:42 +08:00
chenjian	cc8f5312f5	[Feature] Add timestamp for profiler (#4726) ... * [Feature] Add timestamp for profiler * fix bug for offine inference * fix for ci * fix * fix ci	2025-11-05 12:04:59 +08:00
chen	1c3ca48128	[Feature][Executor] GPU Model Runner Supports prompt_logprobs and max_logprobs (#4769)	2025-11-05 10:43:25 +08:00
lzy	af7e0f27f3	supports internode_ll_two_stage (#4162) ... * supports internode_ll_two_stage * supports internode_ll_two_stage * supports internode_ll_two_stage * supports internode_ll_two_stage * supports D internode_ll_two_stage * fix codestype * fix xpu internode_ll_two_stage * fix xpu internode_ll_two_stage	2025-11-04 16:35:40 +08:00
chenjian	25498efcf3	[Optimize] Support and robust for tpN for PD (#4595) ... * [Optimize] Support and robust for tpN for PD * fix * fix * support dpM tpN for cache messager * fix * fix token counter * fix bug for merge develop * fix bug * robust cache messager for v0	2025-11-03 15:38:31 +08:00
chenjian	f83d0cf127	[Feature] Support eplb for fd (#4599) ... * support eplb * support eplb --------- Co-authored-by: kevin <chengyf112@gmail.com>	2025-11-03 14:08:15 +08:00
lizexu123	4ac6de9a3c	[Feature] support pooling model runner (#4590) ... * support qwen3-embedding * support qwen3-embedding-0.6b * fix * fix bug * fix test_return_token_ids.py and update enable_thinking * fix mtp dummy_run * merge develop * fix np.float32 * delete FD_DISABLE_CHUNKED_PREFILL and FD_USE_GET_SAVE_OUTPUT_V1 * delete and build_stream_transfer_data * fix test_update_v1: * fix * fix * update dummy_run post_process * delete test_update_v1 * fix * fix dummy_run * fix model_path * fix model_path * fix dummy_run	2025-10-31 22:32:05 +08:00
kevin	c801d31c9c	add checker (#4711)	2025-10-31 15:26:35 +08:00
李泳桦	0f75b62de2	[BugFix] Fix profile run in pd-disaggregated deployment (#4584) ... * [fix] fix pd+dp+ep bug * [fix] fix again * [ci] fix code style	2025-10-31 14:42:00 +08:00
kevin	64e875b460	[Scheduler] update v1 prefill batch (#4611) ... * update v1 prefill batch * update code * update code	2025-10-31 14:03:01 +08:00
ddchenhao66	b87384aa70	[XPU] xpu currently disable prefix cache for VL model (#4695) ... Co-authored-by: ddchenhao66 <dhaochen163.com>	2025-10-31 10:36:39 +08:00
chen	b73a78155f	fix --logprobs-mode raw_logits (#4681)	2025-10-30 19:53:42 +08:00
zhouchong	35286ce31a	fix total_block_num init error in worker_process (#4687)	2025-10-30 19:53:09 +08:00
kxz2002	7dc9d9885e	[BugFix] fix offline llm chat "enable_thinking" is always "False" (#4686) ... * fix enable_thinking * recover ernie4_5_vl_processor	2025-10-30 19:45:41 +08:00
Jiang-Jia-Jun	f1de348cbf	Update common_engine.py	2025-10-30 14:05:04 +08:00
ltd0924	50be19a88a	[EP] fix several bugs in data parallel (#4657) ... * Simplify profiling block setup in expert_service.py Refactor profiling block initialization to avoid duplication. * Update common_engine.py	2025-10-30 09:50:49 +08:00
ApplEOFDiscord	14f8cddaf1	[Feature] add mm token usage (#4570) ... * add mm token usage * fix unit test * fix unit test * fix unit test * fix model path * fix unit test * fix unit test * fix unit test * remove uncomment * change var name * fix code style * fix code style * fix code style * fix code style * fix unit test	2025-10-29 14:37:12 +08:00
RichardWooSJTU	0dde936e93	[BugFix] fix total_block_num init error in worker_process (#4553) ... * fix total_block_num init error in worker_process * fix req and token client * fix req and token client * fix xpu xi * fix xpu ci	2025-10-28 20:42:12 -07:00
xiaolei373	14e7d88ea4	[feature] support reward api (#4518) ... Co-authored-by: SunLei <sunlei5788@gmail.com>	2025-10-29 00:20:28 +08:00
李泳桦	a012e3608b	[Feature] support logits processors (#4515) ... * [feat] provide an interface for logits processors and a builtin LogitBiasLogitsProcessor * [chore] fix code style * [fix] add unit test & fix existing bugs * [feat] add engine/worker arg --logits-processors * [fix] redefine user args as logits_processors_args and fix some bugs * [fix] fix test_sampler * Update fastdeploy/model_executor/logits_processor/builtin.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update fastdeploy/model_executor/logits_processor/__init__.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Update tests/model_executor/test_logits_processor.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * [fix] fix typo * Update fastdeploy/engine/sampling_params.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * [fix] fix bracelet * [chore] redefine logits processor interface: pass the entire share_inputs into LP, do not copy share_inputs and logits * [doc] add docs * [fix] fix logit bias processor not applied when decoding is too fast & add docs and tests * [fix] fix redundant code * [feat] skip apply() if no bias is specified --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>	2025-10-29 00:08:53 +08:00
ming1753	561b9f38d3	[BugFix] fix paddleocr prefix cache bug (#4625) ... * fix paddleocr prefix cache bug * disable prefix-caching in ocr	2025-10-28 21:38:12 +08:00
SunLei	2a9ed72533	feat: add support for API usage with multimodal models (#4548) ... * feat: add support for API usage with multimodal models * completion_tokens contains num_image_tokens * remove test_request.py * fix: paddle.device.is_compiled_with_cuda() * fix test_unstream_without_logprobs	2025-10-28 20:23:46 +08:00
freeliuzc	c63361fd1d	[Speculative Decoding][MTP]Support mtp in epdptp mode (#4614) ... * support mtp many features * support mtp reshard in rl mode * fix function * support mtp ep * support mtp in hybird-dp-tp mode * default open scheduler_v1 in mtp	2025-10-28 16:02:47 +08:00
Daci	6426414a0f	[Feature] EngineWorkerQueue anonymous port (#4597) ... * EngineWorkerQueue 支持匿名端口设置 * EngineWorkerQueue 支持匿名端口设置 * EngineWorkerQueue 支持匿名端口设置 * EngineWorkerQueue 支持匿名端口设置 * EngineWorkerQueue 支持匿名端口设置	2025-10-28 10:22:37 +08:00
ming1753	7681375a19	[BugFix] PaddleOCR-VL fix FD_DEBUG type and support v1 loader (#4605) ... * [Bug Fix] PaddleOCRVL fix FD_DEBUG type and support HF model * fix bug * fix bug * fix bug	2025-10-28 09:47:47 +08:00
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
chen	5c63a089f6	[Feature] Support logprobs_mode (#4567)	2025-10-27 14:27:48 +08:00
李泳桦	cdc40cdc2a	[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	2025-10-27 10:23:48 +08:00
SunLei	dc1a9c7287	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>	2025-10-25 22:45:38 +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
yyssys	822dea8d5f	[XPU]Moe uses a new operator (#4585) ... * [XPU]Moe uses a new operator * [XPU]Moe uses a new operator * update response	2025-10-24 23:01:46 +08:00
ltd0924	b60ce4922b	[EP] fix adapter bugs (#4572) ... * Update expert_service.py * Update common_engine.py * Update expert_service.py	2025-10-24 12:30:08 +08:00
李泳桦	8edc5cca91	[BugFix] fix create_cache_tensor for ep (#4542) ... * [fix] fix create_cache_tensor for ep * [fix] fix again	2025-10-24 11:31:13 +08:00
xiaozude	f7069b8057	[Metax] adapt DeepSeek (#4498)	2025-10-24 10:14:53 +08:00
RichardWooSJTU	5a8c60454e	[BugFix] Fix decode_type which has been deleted in req and optimize token client retry scheme (#4564)	2025-10-23 05:08:10 -07:00
zhouchong	dce988824d	[Feature] Support AsyncLLM (#4458) ... * add async_llm * apply review * update engine config * Adapt to latest engine.py changes * add more unit tests * Increase unit test coverage --------- Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>	2025-10-22 15:50:12 +08:00
guozhuangzhuang	b6cd3aec70	[Feature] support fd return decode response (#4407) ... * [Feature] support fd return decode response * Resolving conflicts * fix * fix * fix * fix * fix --------- Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>	2025-10-22 14:22:08 +08:00
Yuanle Liu	3b58310c26	enhance set_stop_value_multi_ends and standardize the registration of some operators (#4525) ... * fix custom_ops * paddleformers>=0.3.1	2025-10-21 22:06:06 +08:00
SunLei	809c1ac7ec	feat: add post-processing step for pool_output (#4462) ... * feat: add post-processing step for pool_output * bugfix * fix: test_serving_embedding * fix test_request_to_batch_dicts * fix: code style	2025-10-21 20:24:26 +08:00
SunLei	ee915220bd	[Speculative Decoding] Add draft_logprobs Support for Speculative Decode MTP (#4467) ... * feat: add draft_logprobs for Speculative Decode MTP * feat: add draft_logprobs for Speculative Decode MTP * feat: add draft_logprobs for Speculative Decode MTP * fix: postprocess for speculative decode * test: test_speculative_decoding_use_logprobs * fix: test_completion_echo * fix test_max_streaming_tokens --------- Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>	2025-10-21 14:57:50 +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
李泳桦	b8d235445e	[fix] remove cache tensor creation for cache_transfer_manager (#4420) ... * [fix] remove cache tensor creation for cache_transfer_manager * [fix] fix code style * [fix] fix code style --------- Co-authored-by: ltd0924 <luotingdan@baidu.com>	2025-10-20 16:19:56 +08:00
GoldPancake	47595a2480	[Feature] support mtp logprob (#4464) ... * support mtp logprob * fix unitest	2025-10-20 15:18:12 +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
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
chenjian	670aaa3f83	[Bug fix] Fix pd for x1 thinking (#4433)	2025-10-16 12:03:45 +08:00
ddchenhao66	8e392f0ea6	[XPU] support prefix cache (#4423) ... Co-authored-by: ddchenhao66 <dhaochen163.com>	2025-10-16 11:27:41 +08:00
ltd0924	5bde20b0c9	[BugFix] fix config bugs (#4370) ... * Update expert_service.py * Update common_engine.py * Update expert_service.py * Update expert_service.py * Update expert_service.py --------- Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>	2025-10-16 10:25:21 +08:00