3708 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
a31413510	ace8661b42	change requirements paddleformers==0.4.0 (#5994) v2.3.3	2026-01-12 17:39:36 +08:00
Copilot	b99f6e9519	[Cherry-Pick][Docs] Update GPU version from 2.3.0 to 2.3.2 in installation documentation (#5896) ... * Initial plan * [Cherry-Pick] Update GPU version from 2.3.0 to 2.3.2 in documentation (PR #5894) Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>	2026-01-06 14:15:03 +08:00
bukejiyu	e627e13808	[Cherry-Pick][Loader]Fix bug in MTP weight loading #5744 (#5746) ... * fix mtp * fix --------- Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com> v2.3.2	2025-12-24 22:21:23 -08:00
Jiaxin Sui	47ffaa41b1	[XPU][CI] Update paddlepaddle-xpu installation command	2025-12-25 14:20:05 +08:00
kevin	89675203d3	fix fetch request bug (#5712) v2.3.1	2025-12-24 15:20:56 +08:00
chen	4e392e8337	[BugFix]fix v1 loader lm head fp32 (#5270) (#5287)	2025-11-28 17:52:25 +08:00
Jiaxin Sui	bab01e9f85	[Cherry-pick][XPU][CI] Set pip index URL to Tsinghua mirror (#5277) (#5280) ... * Update run_ci_xpu.sh * Update Docker image tag in CI workflow	2025-11-28 10:14:14 +08:00
kxz2002	9a640b3d6b	[BugFix] unify max_tokens (#4968) (#5119) ... * unify max tokens * modify and add unit test * modify and add unit test * modify and add unit tests --------- Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com> Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>	2025-11-19 19:05:03 +08:00
LiqinruiG	2e4bab35fb	[fix] add more logger info: max_tokens (#5126) ... Co-authored-by: liqinrui <liqinrui@baidu.com>	2025-11-19 18:44:27 +08:00
LiqinruiG	9bb4337143	[BugFix] rollback max_tokens and min_tokens when continue to infer (#5053) ... * [BugFix] rollback max_tokens and min_tokens when continue to infer * [BugFix] rollback max_tokens and min_tokens when continue to infer --------- Co-authored-by: liqinrui <liqinrui@baidu.com>	2025-11-17 19:03:09 +08:00
plusNew001	bd28f18785	[XPU][CI] Ci release update (#5085) ... * Update assertion to check for specific keywords * Remove unused base_response variable Remove unused variable 'base_response'. * Update assertion to check for multiple keywords * Update run_w4a8.py	2025-11-17 19:01:13 +08:00
kxz2002	e92783e903	[BugFix] adjust max_tokens and min_tokens when continue to generate tokens (#5010) (#5013) ... * fix max and min tokens initial commit * fix double subtraction * add unit tests	2025-11-14 18:20:59 +08:00
Yonghua Li	9cec098add	[BugFix] fix num_requests_running after clear_data (#4926) ... * [BugFix] fix num_requests_running after clear_data * [fix] fix tasks_list and stop flags not cleared when _free_blocks failed	2025-11-13 13:50:04 +08:00
BossPi	9590072a91	[Cherry-Pick] [BugFix] Avoid loading training file (#4966) (#4979) ... * [BugFix] Avoid loading training file (#4966) * bug fix don't put scheduler.pdparams into model weights * run pre-commit * bug fix	2025-11-13 10:47:58 +08:00
ming1753	38f6e6c7c6	[BugFix] fix triton fp8 bug (#4967) ... * [BugFix] fix triton fp8 bug * fix bug	2025-11-12 19:28:09 +08:00
plusNew001	bbd9c96ab9	[XPU] [CI]Change CI to multi-concurrency (#4924) ... * Refactor GPU ID logic in CI workflow Updated GPU ID assignment logic and removed unused port variables. * Refactor process handling and update model paths Refactor process termination logic into a function and update model paths for various tests. * Modify service_http_port calculation and clean up code * Modify test_45vl to use dynamic service port and response * Refactor model path and enable tensor parallelism Updated model path retrieval and added tensor parallelism configuration. * Modify service port configuration and cleanup code * Update run_45vl.py * Update health check endpoint to use port variable * Update CI script for paddlepaddle-xpu installation * Replace variable usage with ENDPOINT in script * Refactor EP test script for clarity and efficiency Updated echo statements and removed redundant code for EP tests. * Refactor test_fd_ep function for clarity	2025-11-12 14:43:55 +08:00
ming1753	38ccf9b00b	[Docs] release docs 2.3 (#4951) ... * [Docs] release docks 2.3 * modify dockerfiles * fix bug	2025-11-11 15:30:11 +08:00
chenjian	cba7b2912f	[Opti] Unlimit zmq message lens limit (#4934) v2.3.0	2025-11-10 21:16:36 +08:00
ming1753	197a0f7af4	[BugFix] fix VL fp8 bug when moe token_num is 0 (#4929) ... * [BugFix] fix VL fp8 bug when moe token_num is 0 * fix bug	2025-11-10 21:16:10 +08:00
kxz2002	0a6981f928	[BugFix] Fix inference_start_time (#4922) (#4930) ... * fix inference_start_time * fix inference_start_time	2025-11-10 21:07:52 +08:00
yinwei	2926bf60f7	[XPU][Doc] Update XPU release/2.3.0 documents (#4931) ... * update * update * update * update * update * update --------- Co-authored-by: qw86972190 <127910106+qw86972190@users.noreply.github.com>	2025-11-10 20:07:34 +08:00
luukunn	f7159e31ba	[BugFix] When the value of "temperature" is 0, adjust it to 1e-06 (#4919) ... * 【DataProcessor】add options thinking_mode (#4735) * add thinking_mode * add thinking_mode * add thinking_mode * add thinking_mode * add thinking_mode * add thinking_mode * add unit test * [BugFix] When the value of "temperature" is 0, adjust it to 1e-06 (#4900) * add default temperature value * add unit test * update * update * add unit test * update * fix unit test	2025-11-10 19:34:20 +08:00
plusNew001	c6e9717f33	[XPU][CI]Update test assertion and base response value (#4908)	2025-11-10 12:59:04 +08:00
ming1753	a7ef998e04	[Feature] Optim PaddleOCR-VL (#4872)	2025-11-07 17:55:02 +08:00
plusNew001	329e999f2d	[XPU][CI] Release ci bug fix (#4892) ... * Update run_45T.py * Refactor test_w4a8 to simplify assertions Comment out base response variables and update assertion to check for '人工智能'.	2025-11-07 17:49:41 +08:00
ddchenhao66	51ef990e21	[XPU] modify 424B model deployment parameter (#4887) ... Co-authored-by: ddchenhao66 <dhaochen163.com>	2025-11-07 17:34:49 +08:00
Lucas	3b0bdbae65	[XPU] fix text_image_gather_scatter when image_token_num == token_num && text_token_num == 1 (#4881)	2025-11-07 16:35:49 +08:00
YuBaoku	71bbedaf50	[Cherry-Pick][BugFix][CI] fix vl moe(#4867) (#4869) ... * [CI] update paddlepaddle_gpu==3.2.1 and fix rollout_model test logic * [Cherry-Pick][BugFix][CI] fix vl moe(#4867)	2025-11-07 00:03:36 +08:00
Ayakouji	89934edc10	update (#4851)	2025-11-06 16:08:04 +08:00
kxz2002	cbe27ad9fb	[Cherry-Pick] Fix ernie_vl_reasoning_parsers.py 'end_token' to 'think_end_token' (#4805) (#4842) ... * [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 * [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 * [BugFix] fix offline llm chat "enable_thinking" is always "False" (#4686) * fix enable_thinking * recover ernie4_5_vl_processor * [BugFix] Fix ernie_vl_reasoning_parsers.py 'end_token' to 'think_end_token' (#4805) * fix ernie_vl_reasoning_parsers.py 'end_token' to 'think_end_token' * add unit tests	2025-11-06 15:54:48 +08:00
ApplEOFDiscord	8e48da8027	[Bug Fix] process transparent image (#4807) (#4847) ... * process transparent image * english comments * process transparency at downloading * fix * remove useless codes	2025-11-06 15:43:44 +08:00
RAM	93aedaf23e	temporary fix bug of 0 size tensor (#4844)	2025-11-06 14:20:59 +08:00
RichardWooSJTU	eac823aec8	[BugFix] fix total_block_num init error in worker_process (#4553) (#4817) ... * 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	2025-11-06 13:59:57 +08:00
yinwei	0df488c7bb	support wint8 & wint4 (#4837)	2025-11-06 10:54:34 +08:00
kxz2002	a218291831	[Cherry-Pick] Fix reasoning parser register name (#4795) (#4816) ... * [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 * [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 * [BugFix] fix offline llm chat "enable_thinking" is always "False" (#4686) * fix enable_thinking * recover ernie4_5_vl_processor * fix parser register name (#4795) Co-authored-by: luukunn <83932082+luukunn@users.noreply.github.com> --------- Co-authored-by: luukunn <83932082+luukunn@users.noreply.github.com>	2025-11-06 10:51:40 +08:00
李泳桦	7e7a91855b	[BugFix] fix messages being inplace modified in offline chat api (#4830)	2025-11-05 20:46:55 +08:00
kxz2002	1689f7ef86	[Cherry-Pick] Fix ernie4_5_vl_processor.py and qwen_vl_processor.py can not disable thinking (#4762) (#4798) ... * [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 * [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 * [BugFix] fix offline llm chat "enable_thinking" is always "False" (#4686) * fix enable_thinking * recover ernie4_5_vl_processor * [BugFix] Fix ernie4_5_vl_processor.py and qwen_vl_processor.py can not disable thinking (#4762) * fix ernie4_5_vl_processor.py and qwen_vl_processor.py * add unit test	2025-11-05 10:59:47 +08:00
YuBaoku	7cee8030af	[CI] Disable unstable test jobs and cases (#4799) ... [CI] Disable unstable test jobs and cases	2025-11-05 10:28:53 +08:00
李泳桦	61856e55ce	[fix] fix v0 pd, let worker step_shm_value create=False (#4781) ... Co-authored-by: xiegegege <46314656+xiegegege@users.noreply.github.com>	2025-11-04 20:38:01 +08:00
ming1753	08abb0dd1c	[Docs] Add new support models (#4800)	2025-11-04 16:49:40 +08:00
Lucas	6502d19e97	[XPU] add deploy doc for PaddleOCR-VL in XPU (#4792)	2025-11-04 15:07:04 +08:00
ddchenhao66	78a1451eb7	[XPU] fix thinking bug where output only contains reasoning_content (#4760) ... Co-authored-by: ddchenhao66 <dhaochen163.com>	2025-11-04 12:47:34 +08:00
plusNew001	ffa57dbfac	Modify base_response_104 for better clarity (#4789) ... Updated the base_response_104 message to improve wording.	2025-11-03 22:08:32 +08:00
kevin	cf5e545a73	test scheduler (#4757)	2025-11-03 20:12:02 +08:00
ming1753	e5cbe0d6a1	[Docs] PaddleOCR-VL add RTX3060 server param (#4766) ... * [Docs] PaddleOCR-VL add RTX3060 server param * modify config * fix bug	2025-11-03 19:54:59 +08:00
luukunn	7df7035055	【DataProcessor】add options thinking_mode (#4735) (#4759) ... * add thinking_mode * add thinking_mode * add thinking_mode * add thinking_mode * add thinking_mode * add thinking_mode * add unit test	2025-11-03 18:14:39 +08:00
yyssys	6bfa4fed6e	[Docs]Update XPU document version to 2.3.0 (#4754) ... * [Docs]Update XPU document version to 2.3.0 * update	2025-11-03 13:36:12 +08:00
Yuanle Liu	4d4c13f1b5	[CherryPick] Fix thinking bug cp (#4736) ... * fix thinking bug * fix ut * update * fix v2.3.0-rc0	2025-11-03 11:41:03 +08:00
Jundong Liu	d1d3876c16	[FDConfig] [PD Disaggregation] [Graph Optimization] Close Cudagraph for P node when PD Disaggregation (#4632) (#4734) ... * Close cudagraph for P node when PD Disaggregation * fix problem	2025-11-03 10:59:34 +08:00
YuBaoku	8632b778f5	[CI] update paddlepaddle_gpu==3.2.1 and fix rollout_model test logic (#4738)	2025-11-02 21:30:23 +08:00