3674 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
kevin	64e875b460	[Scheduler] update v1 prefill batch (#4611) ... * update v1 prefill batch * update code * update code	2025-10-31 14:03:01 +08:00
xiaolei373	dde7ba3f9e	[CI]add_tokenizer_cli_unitest (#4620)	2025-10-31 13:57:51 +08:00
ophilia-lee	412097c1b8	benchmark工具支持受限解码场景指定response_format (#4718)	2025-10-31 12:26:24 +08:00
周周周	10de7a3b82	add flops and bandwidth to test_ffn.py (#4704)	2025-10-31 12:13:59 +08:00
Sunny-bot1	9b18f0b55d	cache scale load (#4624)	2025-10-31 11:58:33 +08:00
GoldPancake	1f3ce65b58	[Feature] support mtp distribution equivalence verification (#4699)	2025-10-31 11:45:04 +08:00
Ryan	28de91b50f	[Graph Optimization] SOT+CUDAGraph support ERNIE4.5T VL 28B / 424B (#4645) ... * 45TVL support sot+CUDAGraph * mv unitest from ce_deploy 2 e2e * add test_EB_VL_Lite_sot_serving * rm useless line * add openai_client * fix unitest && reduce computing resources	2025-10-31 11:38:43 +08:00
plusNew001	937bcfc6ed	[XPU] [CI] Lock xvllm version (#4715) ... * Modify XVLLM_PATH assignment in run_ci_xpu.sh Update XVLLM_PATH to point to the newly downloaded xvllm directory. * Lock XVLLM version in CI script Lock XVLLM version to avoid CI issues due to updates. * Change xvllm output download link to latest version Updated the download link for xvllm output to the latest version.	2025-10-31 11:32:38 +08:00
Longzhi Wang	b61a272385	[BugFix] fix unittest of get_save_output_v1 (#4701) ... * [BugFix] fix unittest of get_save_output_v1 * [BugFix] fix unittest of get_save_output_v1 * [BugFix] fix unittest of get_save_output_v1 * [BugFix] fix unittest of get_save_output_v1	2025-10-31 11:23:49 +08:00
kxz2002	a2870ed4a9	[Feature] Unify the registration name recognition for tool_parser and reasoning_parser to “-” (#4668) ... * parser register name unify * change ernie_x1 to ernie-x1 * change ernie4_5_vl to ernie-45-vl * fix unit test	2025-10-31 10:45:27 +08:00
kxz2002	82bd7e5db4	[BugFix] Fix finish reason in _create_chat_completion_choice (#4582) ... * fix n_param _create_chat_completion_choicel * fix unit test * fix final_res * modify unit tests	2025-10-31 10:42:19 +08:00
plusNew001	ea866e4b34	[XPU] [CI] Add Vl case (#4649) ... * Enhance CI script with health checks and logging Updated the CI script to include health checks and logging for the VL model testing process. * Add test for OpenAI chat completions * Refactor chat completion user message structure * Fix variable name for exit code in CI script * Update text prompt to Chinese for artifact question * Update service port and response assertions in tests * Refactor assertion for response content comparison * Update run_45vl.py * Change service HTTP port from 8123 to 8188	2025-10-31 10:38:09 +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
周周周	0089287534	[noauxtc_kernel] remove useless code (#4643) ... * remove num_tokens * remove num_tokens * false * final commit	2025-10-30 18:59:04 +08:00
Jiang-Jia-Jun	ec7746bd55	Update multi-node_deployment.md	2025-10-30 16:40:30 +08:00
Jiang-Jia-Jun	ca52cadd74	Update multi-node_deployment.md	2025-10-30 16:40:08 +08:00
周周周	8b9c9463cd	add real gate_correction_bias weight to mock un-balanced dispatch (#4676)	2025-10-30 15:13:21 +08:00
Jiang-Jia-Jun	f1de348cbf	Update common_engine.py	2025-10-30 14:05:04 +08:00
Haonan Luo	d7d0112bbf	[CI] Add test for paddleocr_vl (#4627)	2025-10-30 13:40:04 +08:00
RAM	cd3b7cc392	[Graph Optimization] Add the CUDAGraph usage switch for Draft Model (#4601) ... * add draft model using cudagraph switch * set default as false * capture draft model in ci * fix bug	2025-10-30 11:44:50 +08:00
ApplEOFDiscord	cfdd1600a5	update doc (#4675)	2025-10-30 11:19:04 +08:00
GoldPancake	fddda50cb9	Add ut for speculative sampler (#4650)	2025-10-30 10:37:49 +08:00
Zhenghai Zhang	1712e1351b	【Hackathon 9th No.86】autogen MoeFastHardamardImplWrapper template_instantiation (#4592) ... * autogen MoeFastHardamardImplWrapper template_instantiation * fix codestyle * fix codestyle * add impl cu files	2025-10-30 10:28:36 +08:00
Ryan	e25c067f70	[OP] Add InferShape&InferDtype for per_token_quant_padding (#4667) ... * add InferShape&InferDtype for per_token_quant_padding * fix codestyle	2025-10-30 10:28:26 +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
周周周	dab04ab413	add noaux_tc to unitest fused_moe (#4656)	2025-10-29 21:50:25 +08:00
plusNew001	fd5015263d	Increase pytest timeout for XPU test (#4665)	2025-10-29 19:57:14 +08:00
kxz2002	c30bfb294f	[Feature] add a new reasoning parser (#4571) ... * add new reasoning_parser initial commit * add parser file content * add register * ernie_test_reasoning_parser * support <tool_call> token and add tool_parser * add and fix unit tests * modify reasoning_parser * modify reasoning parser and tool parser * modify unit tests * modify reasoning_parser and tool_parser * modify unit tests * fix tool_parser * modify the logic of reasoning_parser and tool_parser * add and modify unit tests * standardize code style * simplify reasoning_parser and tool_parser * modify unit test	2025-10-29 18:16:50 +08:00
xjkmfa	19df1aec2b	[Docs] add Qwen25vl yaml (#4662) ... * Add ci case for min token and max token * 【CI case】include total_tokens in the last packet of completion interface stream output * 【CE】add qwen25-vl * 【CE】add qwen25-vl --------- Co-authored-by: xujing43 <xujing43@baidu.com>	2025-10-29 17:39:40 +08:00
Lucas	8f40dfa9bf	[XPU] fix pos_emb_type bug (#4638)	2025-10-29 17:14:32 +08:00
ming1753	d68345cb7e	[Docs] Add PaddleOCR-VL-0.9B best practices (#4658)	2025-10-29 16:48:54 +08:00
ddchenhao66	c92eeed45d	[XPU] Update the return value of TextImageGatherScatter (#4636) ... Co-authored-by: ddchenhao66 <dhaochen163.com>	2025-10-29 16:17:01 +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
RAM	fc5cd1adb1	[BugFix] Fix graph opt test case (#4634) ... * fix bug and refine code * add debug count * refine code * fix ci test case	2025-10-29 13:28:04 +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
zhang-prog	24b9505971	add einops dependency (#4633)	2025-10-28 22:17:13 +08:00
Yuanle Liu	20756cd2bb	fix import jit.marker.unified (#4622)	2025-10-28 22:11:03 +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
RAM	fff5fb5e39	[Graph Optimization] Refactor default capture list (#4617) ... * fix bug and refine code * add debug count * refine code	2025-10-28 21:31:02 +08:00
Lucas	0a0c74e717	[XPU] Support PaddleOCR-VL model for XPU (#4529) ... * [XPU] support PaddleOCR-VL in XPU * [XPU] fix PaddleOCR-VL pos_emb_type	2025-10-28 20:35:04 +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
YuBaoku	e1ac90d787	[CI] Revert test_rollout_model directory change (#4626)	2025-10-28 20:14:00 +08:00
zhouchong	567f61072c	[CI][BugFix] fix port conflicts in concurrent ci test and add more unit test on async_llm (#4616) ... * fix:port conflicts in concurrent ci test * add more unit test on async_llm	2025-10-28 19:04:24 +08:00
yyssys	cd6d1f633c	[XPU]add xpu ci w4a8 case (#4501)	2025-10-28 19:02:29 +08:00
Ryan	07956a87b3	[Graph Optimization] Fix IR graph dependency error exposed after enabling SOT by updating the return value of TextImageGatherScatter (#4610) ... * fix TextImageGatherScatter in sot * fix codestyle	2025-10-28 18:31:23 +08:00