3965 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
YuBaoku	f133ce501c	[CI] disable test_cuda_graph_dynamic_subgraph.py in unit_test	2025-12-11 14:20:53 +08:00
freeliuzc	6715196924	fix attention bug in spec decoding (#5480)	2025-12-10 12:56:13 +08:00
Yuanle Liu	c5973c2087	fix limit_thinking bug (#5477)	2025-12-10 11:50:13 +08:00
lzy	f08fb25cfe	[Others] Maintain the mtp branch temporarily. (#5447)	2025-12-09 19:41:33 +08:00
kevin	9b5b08cb72	[Cherry-Pick][BugFix] Fix async download(#5349) (#5347) ... * fix mm to_dict bug * pd support async download * update code * update test case * update log * Revert "update log" This reverts commit 6e883150cd. * update code * fix mtp bug	2025-12-05 18:59:36 +08:00
lzy	cae2c1ccf5	supports mtp split_kv_attn (#5344)	2025-12-03 13:33:26 +08:00
lzy	04b2c43806	[Optimization] 1.fix tp+ep moe_forward; 2.set max_prefill_batch=env.MAX_PREFILL_NUM (#5316)	2025-12-02 13:03:55 +08:00
kevin	f1e1f5da57	fix mm to_dict bug (#5299)	2025-11-29 20:49:36 +08:00
Yuanle Liu	b99064432e	Update load_weight_utils.py (#5285)	2025-11-28 13:39:59 +08:00
Jiaxin Sui	89ed1a9e84	[Cherry-pick][XPU][CI] Set pip index URL to Tsinghua mirror (#5277) (#5281) ... * Set pip global index URL to Tsinghua mirror * Update Docker image tag in CI workflow	2025-11-28 10:13:41 +08:00
lizhenyun01	fd1313cdb4	[Cherry-Pick][Feature] support flash_mask_attention backend(#5134) (#5256) ... * [Feature] suppert flash_mask_attention backend * fix unittest * clean code	2025-11-28 10:13:00 +08:00
Yuanle Liu	9b0c65ba57	Add method to disable sequence parallel MoE if needed (#5268)	2025-11-27 16:28:24 +08:00
kevin	69b4d058ad	cp_fix_bug (#5253)	2025-11-27 15:15:49 +08:00
SunLei	3d74a4baf6	[Cherry-Pick] MTP split draft_tokens into standalone post-processing path(#5205) (#5231) ... * refactor(mtp): split draft_tokens into standalone post-processing path for MTP + logprobs * Restore Request.__repr__ implementation * ci * add envs * fix unittest	2025-11-27 11:23:38 +08:00
freeliuzc	bdcc952eeb	fix pd-split first step bug (#5246)	2025-11-26 18:02:32 +08:00
xiaoxiaohehe001	710753377f	[Cherry-Pick] Fix eplb noaux(#5239) (#5240) ... * fix eplb noaux * fix eplb noaux	2025-11-26 17:51:10 +08:00
YuBaoku	49be443d02	[Cherry-Pick][CI] Add check trigger and logic(#5191) (#5227) ... * [CI] Add Cherry-Pick PR check logic (cherry picked from commit 8bc2e13fdafaf339ebe518d7e5dccdbd8ff3fc2d) * [Cherry-Pick][CI] Add check trigger and logic	2025-11-26 13:20:38 +08:00
kevin	e0c7ebff29	[BugFix][Cherry Pick] fix ds type bug (#5220) ... * fix ds type bug * update code	2025-11-25 20:37:09 +08:00
freeliuzc	a11d17cee9	[Speculative Decoding][Cherry Pick]Update extract_mtp_weight script and optimize config (#5213) ... * update extract_mtp_model * modify config usage	2025-11-25 14:42:55 +08:00
freeliuzc	e581b7d7d9	fix kernel output extract (#5212)	2025-11-25 14:25:20 +08:00
Echo-Nie	a418d7b60b	[CI] Add Unittest (#5187) ... * add test * Delete tests/model_executor/test_w4afp8.py * Rename test_utils.py to test_tool_parsers_utils.py * add test * add test * fix platforms * Delete tests/cache_manager/test_platforms.py * dont change Removed copyright notice and license information.	2025-11-25 11:00:34 +08:00
Jiang-Jia-Jun	717da50b40	Update pull_request_template.md	2025-11-25 10:32:19 +08:00
Jiang-Jia-Jun	86d6ee90be	Update pull request template warning message	2025-11-25 10:11:33 +08:00
Jiang-Jia-Jun	6b111ef900	Update pull_request_template.md	2025-11-25 10:10:17 +08:00
zccjjj	ea3bc5b4ca	[XPU] Fix the error in MoeExpertFFN operator when valid_token_num=0 (#5196)	2025-11-25 10:07:20 +08:00
chenjian	09b47c7111	[Bug fix] Send first token in D instance (#5199) ... * [Bug fix] Send first token in D instance * fix	2025-11-24 23:42:20 +08:00
YuBaoku	95b39317a9	[CI] Update redis download source (#5198)	2025-11-24 21:14:59 +08:00
Yuanle Liu	f69e0839f7	dummy import fd (#5192)	2025-11-24 20:23:07 +08:00
kevin	8e4e3ff510	[Feature] support eplb in api_server (#4782) ... * support eplb in api_server * update code * add eplb test case * update eplb * support tp+dp eplb * update test cese * update code * update code * fix bug * update copilot review * update test case name	2025-11-24 20:22:29 +08:00
xiaozude	d5bd64336a	[Metax] support ENABLE_V1_KVCACHE_SCHEDULER (#5163)	2025-11-24 19:19:49 +08:00
xiaoxiaohehe001	e150a418d4	support moe offline quant (#5142)	2025-11-24 18:59:18 +08:00
Jiaxin Sui	5ff93d4998	[XPU][CI] change VL model to 28B-VL-thinking (#5169) ... * Enhance run_ci_xpu.sh with caching and prefill options * Update model path and configuration in run_ci_xpu.sh * Add '北朝' keyword to assertion in run_45vl.py * Enhance process termination logic in run_ci_xpu.sh * Set timeout for CI_XPU job to 60 minutes * Remove extra newline in stop_processes function	2025-11-24 16:50:18 +08:00
Juncai	af03da5127	[BugFix] fix release block ids (#5184) ... * fix release block ids * up	2025-11-24 16:48:09 +08:00
xunyoyo	7bac016c77	[CI] 【Hackathon 9th Sprint No.18】NO.18 功能模块单测补充 (#5064) ... * Add unit tests for DeepEP buffer functionality This file contains unit tests for the DeepEP buffer helpers and runners, including various test cases for buffer allocation, cleanup, and dispatching processes. * Refactor DeepEP tests to use scoped stubs * Add licensing information to test_ep.py Added licensing information to the test file.	2025-11-24 15:52:34 +08:00
xiaoxiaohehe001	95f3c8c641	[Fix] Fix eplb bug and support fp8 load weight (#5178) ... * fix eplb part2 * fix eplb part2 * fix eplb part2	2025-11-24 15:31:37 +08:00
qw86972190	f5c1066245	[XPU]Update documentation (#5180) ... * [XPU]Update document * [XPU]Update documentation	2025-11-24 14:00:51 +08:00
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