3929 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
YuBaoku	98f1ab46a9	[CI] add output for last_token in test_streaming_with_stop_str (#5170)	2025-11-24 10:49:17 +08:00
Nyakku Shigure	b9e76f1a7a	[Coverage] Ignore new custom ops stub file in codecov (#5177)	2025-11-23 22:33:28 +08:00
周周周	e297406263	[Others] unitest tests/layers/test_attention_layer.py (#5174)	2025-11-23 22:21:01 +08:00
YuBaoku	5daa8d0686	[CI] fix coverage_report in daily test (#5175) ... * [CI] fix coverage_report in daily test	2025-11-23 21:48:11 +08:00
megemini	c06cfe2447	【Hackathon 9th No.109】[CppExtension] 添加 fastdeploy_ops 目录到 package_data 以支持现代打包方式 (#5156) ... --------- Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com> Co-authored-by: SigureMo <sigure.qaq@gmail.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>	2025-11-22 01:32:06 +08:00
kevin	cceaba1c8d	[Feature] remove to_numpy (#5162) ... * remove to_numpy * update code * update name * update code * update code * update code	2025-11-21 21:54:26 +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
GoldPancake	ab3a2e45ff	fix mtp reschedule (#5165)	2025-11-21 19:31:35 +08:00
chenjian	3ea1b44a58	[Optimization] Improve perf for fd response token with internal adapter (#4992) ... * [Optimize] Improve perf for fd response token with internal adapter * fix * fix bug * fix ci * fix ci * fix ci * fix ci	2025-11-21 19:02:03 +08:00
Yuanle Liu	5bcf79d780	[BugFix] fix num of rdma_comm_ports check (#5168) ... * fix num of rdma_comm_ports check * update * update * update	2025-11-21 18:31:14 +08:00
Jiang-Jia-Jun	d2298dcb0c	[Polish] Simplify __repr__ method in Request class (#5153) ... Remove detailed string representation for Request class.	2025-11-21 17:21:06 +08:00
xiaoxiaohehe001	6471dade4a	[Fix] Fix noaux ep test (#5161) ... * support noaux eplb * noaux_eplb * noaux_eplb * noaux_eplb * noaux_eplb	2025-11-21 16:36:41 +08:00
Juncai	f9b0545a7f	[PD Disaggregation] [Refine] Refine splitwise deployment (#5151) ... * Refine splitwise deployment * up	2025-11-21 15:30:24 +08:00
freeliuzc	2d1dade5e2	[Speculative Decoding][MTP] Support static CacheKV C8 quantization and optimize memory usage (#5155) ... * support static cachekv c8 quantization in mtp mode * optimize memory allocation	2025-11-21 15:10:13 +08:00
lizhenyun01	3c36283d7d	[ENV] support AK SK ENCPOINT while get the multi_modal's feature (#5159)	2025-11-20 23:07:57 -08:00
bukejiyu	34f59d9800	[RL]Fix missing is_distributed attribute (#5150) ... * fix * update	2025-11-21 14:14:25 +08:00
xiaoxiaohehe001	6ca2651995	[Feature] Support noaux for eplb (#5143) ... * support noaux eplb * noaux_eplb * noaux_eplb * noaux_eplb	2025-11-21 14:10:32 +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
essos	79f18331b6	[CI]【Hackathon 9th Sprint No.51】NO.51 功能模块 fastdeploy/scheduler/dp_scheduler.py 单测补充 (#5046) ... * update test utils * Add comprehensive unit tests for DP scheduler functionality - Add test_dp_scheduler.py with full-featured unit tests supporting both normal and standalone modes - Add test_dp_scheduler_simple.py with lightweight mock-based tests for easy execution - Add comprehensive README.md documenting test architecture and usage - Tests cover DPLocalScheduler and DPScheduler classes with focus on: - Request lifecycle management and TTL support - Response handling and routing - Resource-based scheduling and constraint handling - Multi-threading and concurrent operations - Splitwise role support (prefill vs decode) - Error handling and edge cases - Thread-safe operations with proper synchronization 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * Remove tests/multimodal/test_utils.py This file appears to be duplicate or misplaced, removing it to clean up the test structure. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * update * fix * rm unused file --------- Co-authored-by: Claude <noreply@anthropic.com>	2025-11-21 10:52:33 +08:00
YuBaoku	0b0f2e320e	[CI] Unified diff coverage upload logic (#5127) ... * [CI] fix diff_coverage_report upload	2025-11-21 10:50:57 +08:00
kevin	7454480e07	[Feature] support bos download retry (#5137) ... * support bos download retry * update code * update code	2025-11-21 10:18:32 +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	01c30f6b87	Fix schedule error in splitwise deployment (#5149)	2025-11-20 21:18:10 +08:00
Jundong Liu	147b2e5eb0	[BugFix] Fix zero workspace returned by CUB size query under CUDA Graph in MoE dispatch (#5087) ... * fix bug about CubKeyValueSorter::run * pre-commit and add comment * pre-commit * Apply suggestion from @Copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * fix precommit --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>	2025-11-20 20:00:29 +08:00
Ryan	0857099191	mv import (#5146)	2025-11-20 19:25:56 +08:00
Jiaxin Sui	c3994750b1	[CI][XPU] Add XPU chunked_prefill && prefix_caching case (#5139)	2025-11-20 18:51:50 +08:00
周周周	385fe6dade	[Others] clean code (#5133)	2025-11-20 18:44:08 +08:00
Yuanle Liu	7ac25935c7	[Optimization] default compile rdma, reduce cudagraph buffer size in mm, fix some config bug (#5121) ... * default compile rdma, reduce cudagraph buffer size in mm, fix some config logic * update * update * fix bug * enhance rdma compile * fix	2025-11-20 17:19:47 +08:00
周周周	6fa34102e8	[Others]get_block_shape_and_split_kv_block clean code (#5123)	2025-11-20 16:40:04 +08:00
yangjianfengo1	af715db763	[Scheduler] Support chunk prefill for video input (#5107) ... * add video chunk prefill * add vit_merge=True for test_tokenizer_client.py --------- Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>	2025-11-20 16:29:13 +08:00
Neil Zhu	0edda75a56	[Metax] optimize cutlass moe and flash attention backend (#5128)	2025-11-20 16:12:35 +08:00
freeliuzc	f1e36ff2f7	[Speculative Decoding][MTP]Support stop_seqs and pd-split mode (#5029) ... * support multi_stop_seqs in speculative decoding * support mtp tp with ep split * fix custom op register * fix spec stop_seqs params	2025-11-20 15:26:01 +08:00
plusNew001	3e3558f492	[HPU][CI]Hpu ci update (#5116) ... * Update Docker image in CI workflow * Update pip configuration and uninstall packages Set pip global index URL to Tsinghua mirror and uninstall PaddleCustomDevice and fastdeploy.	2025-11-20 14:12:52 +08:00
YuBaoku	e021048318	[CI] Temporarily lock paddlepaddle-gpu as of 20251118 (#5136)	2025-11-20 11:15:08 +08:00
kevin	109d48e456	[Feature] support async download features (#5003) ... * support async download features * add test case * update code	2025-11-19 22:23:36 +08:00
Sunny-bot1	bde97e09f7	support dynamic activation quant for w4afp8 (#5117)	2025-11-19 21:11:16 +08:00
YuBaoku	2716da4220	[CI] Add workflow to auto-remove skip-ci labels after new commits (#5129) ... * [CI] Add CI to automatically remove skip-ci labels after new commits	2025-11-19 19:22:06 +08:00
LiqinruiG	a5cd7c9039	[BugFix] rollback max_tokens and min_tokens when continue to infer (#5082) ... * [BugFix] rollback max_tokens and min_tokens when continue to infer * [BugFix] rollback max_tokens and min_tokens when continue to infer * [fix] add more logger info: max_tokens --------- Co-authored-by: liqinrui <liqinrui@baidu.com>	2025-11-19 18:43:42 +08:00
Sunny-bot1	43f0c7557e	[Feature] Add an unquantized option for MoE and Dense quant type (#4813)	2025-11-19 16:24:03 +08:00
chen	9ff418db73	check METAX_GPU (#5114)	2025-11-19 16:02:21 +08:00
tianlef	de43577a7c	[Docs] add ebvlthinking yaml (#5120)	2025-11-19 15:27:46 +08:00
megemini	3c8c0f0d6c	【Hackathon 9th No.109】[CppExtension] [XPU] Support build Custom OP in setuptools 80+ -part (#5106) ... * [CppExtension] 添加现代Python打包方法兼容性支持 * [CppExtension] 移除构建脚本中的错误退出逻辑 * [CppExtension] 移除现代Python打包兼容性代码，仅保留传统打包方式 * [CppExtension] 恢复现代Python打包兼容性支持并优化目录检测逻辑	2025-11-19 13:33:39 +08:00
Zhang Yulong	be9541a97b	[CI] add metrics case (#5115) ... * add case * add case	2025-11-19 11:50:12 +08:00
YuBaoku	24e9e2d9c8	[CI]Exclude abstract methods and irrelevant backend files (#5031)	2025-11-19 11:48:28 +08:00
bukejiyu	a82f25ea7b	[RL]Resolve shape mismatch problems in RL-related modules (#5032) ... * RL fix * update	2025-11-19 11:12:48 +08:00
Winters Montagne	4694ed2a43	[CI]【Hackathon 9th Sprint No.31】NO.31 功能模块 fastdeploy/input/ernie4_5_processor.py 单测补充 (#5097) ... * Add unit tests for ernie4_5_processor * update * update	2025-11-19 10:51:02 +08:00
qw86972190	857d152464	[XPU][Docs]Update document (#5091)	2025-11-19 10:20:14 +08:00
Daci	eab8384da6	[Feature] ThreadPoolExecutor async fill_token_bitmask (#5083) ... * ThreadPoolExecutor async fill_token_bitmask * ThreadPoolExecutor async fill_token_bitmask logging * fix test_guided_decoding * Apply suggestions from code review Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * add fill_bitmask_parallel_batch_size ENV * FD_FILL_BITMASK_BATCH fastdeploy.envs --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>	2025-11-19 10:04:16 +08:00
K11OntheBoat	4a7739ec0b	Fix dummy run when use PD Disaggregation with EP inference. (#5112) ... Co-authored-by: K11OntheBoat <“ruianmaidanglao@163.com”>	2025-11-18 21:09:30 +08:00
plusNew001	7fdc920a01	[HPU][CI]Update Docker image in CI workflow (#5108)	2025-11-18 20:43:19 +08:00