50 Commits

Author	SHA1	Message	Date
kevin	23bfd28624	[Cherry-Pick][BugFix] cp fix_cpu_cache_bugs(#5544) (#5577) ... * cp fix_cpu_cache_bugs * update ce case * update test case * update code	2025-12-19 11:48:50 +08:00
Yonghua Li	f4119d51b4	[PD Disaggregation] support DP via v1 router and decouple DP and EP (#5197) ... * [fix] support DP via v1 router and decouple DP and EP * [fix] fix scripts * [fix] reset model path * [fix] dp use get_output_ep, fix router port type, update scripts * [merge] merge with latest code * [chore] remove some debug log * [fix] fix code style check * [fix] fix test_multi_api_server for log_dir name * [chore] reduce logs * Apply suggestions from code review Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>	2025-12-04 15:38:43 +08:00
K11OntheBoat	2e1680838f	[PD Disaggregation] Support PD deployment of DeepSeekv3. (#5251) ... * Support deepseekv3 cache transfer for PD deploy * clean some log info --------- Co-authored-by: K11OntheBoat <“ruianmaidanglao@163.com”>	2025-12-02 14:11:50 +08:00
Juncai	0925d44f18	[PD Disaggregation] support different tp_size for prefill and decode (#5296) ... * up * up * up * fix	2025-12-01 17:50:20 +08:00
Yonghua Li	cead6b26fa	[Metrics] Update time_to_first_token to include tokenization & queue time, and remove redundant metrics (#4993) ... * [update] update time_to_first_tokens to include queue time, and remove first_token_latency and infer_latency * [doc] update docs * [ci] fix test * [chore] delete redundant code --------- Co-authored-by: Jiaxin Sui <95567040+plusNew001@users.noreply.github.com>	2025-11-26 14:42:17 +08:00
Yuanle Liu	f69e0839f7	dummy import fd (#5192)	2025-11-24 20:23:07 +08:00
kevin	c068a4f642	[Feature] dyc8 support prefixcache (#5125) ... * dyc8 support prefixcache * fix cache_trans test case * update code	2025-11-21 19:46:26 +08:00
ddchenhao66	e70e2279ce	[PD Disaggregation][XPU] Add XPU support for PD disaggregation (#5113) ... * [XPU] xpu support PD disaggregation * [XPU] fix the issue of cache KV transfer process startup failure on non-zero XPU cards * [XPU] xpu support PD disaggregation in v1 scheduler --------- Co-authored-by: ddchenhao66 <dhaochen163.com>	2025-11-21 14:09:01 +08:00
Yonghua Li	43097a512a	[BugFix] [PD Disaggregation] fix v1 scheduler prefill node profile run & ipc transfer protocol (#5132) ... * [fix] fix v1 scheduler profile run for append attention in prefill node * [fix] skip send_signal if kv signal not inited for gpu and xpu * [fix] extend fix to flash_attn & mla_attn * [fix] fix v1 pd run in ipc transfer protocol * [ci] add test for v1 pd profile run using ipc transfer protocol * [style] fix code style check * [style] fix code style again * [fix] fix profile run * [update] remove --num-gpu-blocks-override in example script * [chore] rename forward_meta is_profiling to is_dummy_or_profile_run	2025-11-20 21:39:22 +08:00
Juncai	36822fa49c	[PD Disaggregation] remove splitwise deployment on single node and refine the code (#4891) ... * remove splitwise deployment on single node and refine the code * up * up * up * add test * up	2025-11-14 09:56:53 +08:00
ltd0924	5bf48de999	[KVCache] support unified cache backend (#4903) ... * [Feature] support unified cache backend * fix * fix * fix * fix * Update metax_model_runner.py * fix * update * Update test_moba_attention_backend.py --------- Co-authored-by: ltd0924 <luotingdan@baidu.com>	2025-11-12 14:54:52 +08:00
chenjian	78895e2c7d	[Bug Fix] fix bug for PD EP (#4823) ... * fix bug for PD EP * fix * optimize perf for engine worker queue * fix bug * fix internode ll two stage * fix for ci * fix bug	2025-11-10 15:33:29 +08:00
kevin	cc34487810	[Feature] support mm disable_chunked (#4803) ... * support mm disable_chunked * update code * update code * update code	2025-11-06 21:32:25 +08:00
Juncai	08ca0f6aea	[Feature] [PD] add simple router and refine splitwise deployment (#4709) ... * add simple router and refine splitwise deployment * fix	2025-11-06 14:56:02 +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
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
zhupengyang	3a6883ac1a	c++ code format (#4527)	2025-10-22 17:59:50 +08:00
ltd0924	fb76cdfb4f	[Fearture] Support mm model close prefix cache (#4459) ... * [Feature] support prefix cache in DP * fix * Update common_engine.py * Update common_engine.py * Update common_engine.py * Update common_engine.py * [BugFix] fix workers more than 1 * fix * Update api_server.py * fix * Update api_server.py * fix * [Fearture] Support mm model close prefix cache * Update api_server.py * Update engine_client.py * Update engine_client.py * add test * Update test_chat.py * fix * fix * Update test_chat.py * Update test_chat.py --------- Co-authored-by: ltd0924 <luotingdan@baidu.com> Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>	2025-10-21 15:37:59 +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
ddchenhao66	14785eb65d	[XPU] abstract a hardware-agnostic operator wrapper for prefix cache and specify xpu device id definition (#4455) ... Co-authored-by: ddchenhao66 <dhaochen163.com>	2025-10-17 14:05:33 +08:00
xiaolei373	d1637db86a	modify_comment (#4460)	2025-10-17 10:10:09 +08:00
xiaolei373	dbca63f862	[bugfix] kill cache_transfer_manager process (#4401)	2025-10-16 20:45:24 +08:00
ddchenhao66	8e392f0ea6	[XPU] support prefix cache (#4423) ... Co-authored-by: ddchenhao66 <dhaochen163.com>	2025-10-16 11:27:41 +08:00
李泳桦	ffe7af8a97	[fix] fix requests & block metrics (#4404) ... * [fix] fix requests & block metrics * [chore] rename variables	2025-10-15 11:49:24 +08:00
李泳桦	70633c6641	[fix] fix gpu_caches key (#4311)	2025-09-28 21:32:57 +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
chenjian	3cef851468	[Bug fix] Fix bug for running ep (#4245) ... * fix bug for ep * fix bug	2025-09-28 14:56:18 +08:00
Zero Rains	b433a93d9a	fix the bug for prefilled_step_idx signal of cache_messager in cudagraph and PD (#4235)	2025-09-24 19:46:52 +08:00
chenjian	918ccdb123	[Feature] Support pd ep deployment with yiyan adapter (#4029) ... * [Feature] Support mixed deployment with yiyan adapter in release2.2 * fix metrics * add unit test * add unit test * add unit test * Support pd ep deployment with yiyan adapter * Support pd ep deployment with yiyan adapter * refactor cache messager * support scheduler v1 in PD * suppport pd v1 + chunk prefill * suppport pd v1 + chunk prefill * add eplb * support eplb * support eplb * support eplb * support v1 * fix * fix * fix bug * remove eplb support * support prefix cache in P * fix bug * fix bug * support one stop in V1 * fix bug * fix ci * fix ci * fix * fix * fix * fix * fix --------- Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>	2025-09-22 16:41:38 +08:00
Zero Rains	f213ae1e86	[Bug Fix]fix the bug for cache_messager signal loss (#3879) ... * fix the bug for real size 0 in cudagraph * fix cache_messager	2025-09-15 11:16:24 +08:00
chenjian	37f1632732	[Optimize] optimize prefix cache in develop (#3890) ... * optimize prefix cache in release22 * fix * fix * fix * add ci for v1 * add unit test --------- Co-authored-by: xiegegege <46314656+xiegegege@users.noreply.github.com>	2025-09-12 10:15:59 +08:00
qwes5s5	17169a14f2	[metrics] Add serveral observability metrics (#3868) ... * Add several observability metrics * [wenxin-tools-584] 【可观测性】支持查看本节点的并发数、剩余block_size、排队请求数等信息 * adjust some metrics and md files * trigger ci * adjust ci file * trigger ci * trigger ci --------- Co-authored-by: K11OntheBoat <your_email@example.com> Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>	2025-09-08 14:13:13 +08:00
co63oc	d6369b4d51	fix typos (#3684)	2025-09-01 17:50:17 +08:00
chenjian	465065cd19	[Bug fix] Fix prefix cache in V1 (#3715) ... * [Bug fix] Fix prefix cache in V1 * fix code style	2025-08-31 21:29:33 +08:00
李泳桦	98e03fb4ea	[feat] add metrics for yiyan adapter (#3219) (#3614) ... * [feat] add metrics for yiyan adapter * [fix] fix metrics num_requests_waiting and num_requests_running * [fix] fix metrics gpu_cache_usage_perc * [refactor] change where requests_number increases * [chore] rename xxx_block_num as xxx_gpu_block_num, and update their values accordingly * [chore] delete useless code	2025-08-30 23:20:58 +08:00
Zero Rains	f206474cc7	fix the bug when num_key_value_heads < tensor_parallel_size (#3717)	2025-08-30 12:40:00 +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
kevin	67298cf4c0	add error traceback info (#3419) ... * add error traceback info * update error msg * update code --------- Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>	2025-08-19 19:32:04 +08:00
chenjian	b21272d9ff	[Bug fix] fix block num setting in scheduler v1 for develop (#3303) ... * fix block num setting in scheduler v1 * fix block num setting in scheduler v1 * fix max_block_num and max_num_batched_tokens setting * fix max_block_num and max_num_batched_tokens setting * fix max_block_num and max_num_batched_tokens setting * fix max_block_num and max_num_batched_tokens setting	2025-08-12 10:38:51 +08:00
ltd0924	c9e6ce1518	Update cache_messager.py (#3172)	2025-08-04 14:32:34 +08:00
chenjian	fe17410f9c	[BUG] Fix bug for pd in fd (#3034) ... * Fix bug for pd in fd * Fix bug for pd in fd --------- Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>	2025-07-31 20:17:27 +08:00
kevin	22cab724e8	[Feature] block scheduler v1 support prefix caching (#3061) ... * block scheduler v1 support prefix cache * update code * update code * fix code bug * add timeout time --------- Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>	2025-07-31 19:29:19 +08:00
YuanRisheng	7dfdd157ac	[BugFix]Fix ep size (#3092) ... * fix ep * fix num_layer	2025-07-30 21:03:12 +08:00
Zhida Hu	3f8a41e68c	[*] fix the memory leak when modify qp to rts failed (#3051) ... Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>	2025-07-30 19:49:07 +08:00
YuanRisheng	1a815b7a2a	Fix Speculative Config bug (#3049) ... * fix speculative bug * fix rl	2025-07-29 10:50:48 +08:00
Zero Rains	0fb37ab7e4	update flake8 version to support pre-commit in python3.12 (#3000) ... * update flake8 version to support pre-commit in python3.12 * polish code	2025-07-24 01:43:31 -07:00
chenjian	85a78d695d	[Feature] Support block scheduler v1 for FD (#2928) ... * Support FD block scheduler v1 * Support FD block scheduler v1 * Support FD block scheduler v1 * Fix according to copilot review * Fix according to review * Remove is_dummy * Fix bug when real_bsz=1 * Fix infer first token cost time --------- Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>	2025-07-23 20:31:31 +08:00
Zero Rains	25698d56d1	polish code with new pre-commit rule (#2923)	2025-07-19 23:19:27 +08:00
ltd0924	68b4755587	[LLM] support multi node deploy (#2708) ... * [LLM] support multi node deploy * Update engine.py * fix bugs * fix * [LLM] support multi node deploy * [LLM] support multi node deploy --------- Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>	2025-07-06 10:33:51 +08:00
Jiang-Jia-Jun	92c2cfa2e7	Sync v2.0 version of code to github repo	2025-06-29 23:29:37 +00:00