154 Commits

Author	SHA1	Message	Date
fmiao2372	404cf0ece4	[Intel HPU] enable tensor_wise_fp8 (#5324) ... * [Intel HPU] enable tensor_wise_fp8 * update code based on comments * fix code style issue * fix bug about RP 5138 * mv kv_cache modifications to HPU backend * fix FP8 Precision Issues * fix FP8 Precision Issues * Add quantization UT --------- Co-authored-by: yanfeich <yanfei.cheng@intel.com> Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>	2025-12-17 16:45:03 +08:00
Ryan	4eb55332f6	[Models] Add forward_meta to VocabParallelEmbedding of all models (#5524)	2025-12-12 14:11:31 +08:00
kevin	954a145d57	[Optimization] support mm prefill batch (#5313) ... * support mm prefill batch * update code * update code * update code * update code * fix encoder cache bug * update code * update code * fix bug * fix paddle ocr bug * fix xpu bug * update code	2025-12-11 22:21:14 +08:00
Ryan	e58fed3665	[Graph Optimization][BugFix][CI] Fix 0size bug && add unitest (#5495)	2025-12-11 16:25:26 +08:00
Haonan Luo	e397c4fba6	[Others] remove add_bias option (#5425)	2025-12-09 17:39:35 +08:00
Nyakku Shigure	e1c4a12e34	[Graph Optimization][CINN] Use CINN in PaddleOCR-VL ViT part (#5223) ... --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>	2025-12-09 14:37:00 +08:00
xiaozude	c06a6234b9	[Metax] optimize mla attention (#5258)	2025-12-09 11:18:19 +08:00
Nyakku Shigure	0c66163dfd	[Loader][BugFix] Fix some parameters place on CPU in PaddleOCR-VL (#5413) ... * [BugFix] Fix some parameter place on CPU in PaddleOCR-VL * clean log * fix codestyle	2025-12-08 10:01:00 +08:00
RAM	b2908b8e82	[New][RL] Support Rollout Routing Replay (#5405) ... * [RL] Support Rollout Routing Replay * add routing indices cache * fix config bug and moe forward bug * R3 Support GLM * support eb4.5 * fix merge bug * Apply suggestion from @Copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Apply suggestion from @Copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Apply suggestion from @Copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Apply suggestion from @Copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * add routing replay ci * support glm topk * support orther top_k * fix ci bug * pre-commit * only support chatcmpl * Revert "Revert "[RL] Support Rollout Routing Replay (#5321)" (#5402)" This reverts commit c45e064f3d. * Fix XPU and NPU bug --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Yuanle Liu <yuanlehome@163.com>	2025-12-05 22:06:26 +08:00
Jiang-Jia-Jun	c45e064f3d	Revert "[RL] Support Rollout Routing Replay (#5321)" (#5402) ... This reverts commit 96d2d4877b.	2025-12-05 20:19:39 +08:00
RAM	96d2d4877b	[RL] Support Rollout Routing Replay (#5321) ... * [RL] Support Rollout Routing Replay * add routing indices cache * fix config bug and moe forward bug * R3 Support GLM * support eb4.5 * fix merge bug * Apply suggestion from @Copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Apply suggestion from @Copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Apply suggestion from @Copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Apply suggestion from @Copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * add routing replay ci * support glm topk * support orther top_k * fix ci bug * pre-commit * only support chatcmpl --------- Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Yuanle Liu <yuanlehome@163.com>	2025-12-05 20:01:33 +08:00
Longzhi Wang	5cd17fd662	[Models] Add forward_meta to moe models' forward function (#5138) ... * [Models] Add forward_meta to moe models' forward function * fix missing param * fix * fix * fix forward_meta * fix test and remove chunked MoE releated in config * fix test * fix * fix	2025-12-04 13:26:58 +08:00
lizexu123	c563eca791	[Feature] support reward model (#5301) ... * Your commit message here * add test * update develop * support reward * support enable_chunk_prefill * support bingfa * support convert is reward * update test * delete print * fix enable_thinking * add document * fix place * fix test * fix * support enable_prefix_caching * add no-enable_prefix-caching test * fix * support enable_prefix_caching * delete print * fix document * fix * fix test * fix document and delete chinese * udpate * enable_thinking * fix test	2025-12-02 14:55:31 +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
chen	aa35ce449d	[Optimization] EP empty_input_forward Remove Communication (#5254)	2025-12-01 21:10:40 +08:00
bukejiyu	1539fd6056	[BugFix]Set default OMP_NUM_THREADS=3 and fix extra GPU memory usage in DeepSeek (#5219) ... * fix bug * update * update * update * fix copy * update	2025-11-28 14:22:04 +08:00
chen	35f85baf09	[BugFix]fix v1 loader lm head fp32 (#5270)	2025-11-27 20:12:56 +08:00
Yuanle Liu	cb56d46694	[Optimization] Refine row parallel bias and nranks and moe all_reduce (#5247) ... * rename nranks to tp_size and fix bias in v1 loader * fix * update	2025-11-26 05:09:09 -08:00
chen	209970836e	[BugFix] BF16 MoE Cutlass Backend Support EP (#5242)	2025-11-26 19:16:22 +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
xiaoxiaohehe001	e150a418d4	support moe offline quant (#5142)	2025-11-24 18:59:18 +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
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
bukejiyu	a82f25ea7b	[RL]Resolve shape mismatch problems in RL-related modules (#5032) ... * RL fix * update	2025-11-19 11:12:48 +08:00
周周周	51b1f13547	[Executor]move batch_id_per_token (#4853)	2025-11-14 15:38:48 +08:00
xiaozude	c45b3ccb52	[Metax] optimize flash mla (#4915)	2025-11-12 16:43:46 +08:00
bukejiyu	b09ebb2813	refactor pt loading (#4532)	2025-11-11 21:30:39 +08:00
Ryan	07a82afcae	add tie_word_embeddings for lmhead (#4916)	2025-11-11 10:46:35 +08:00
Yuanle Liu	3dc0ffa46d	[TSP] Support qwen3 moe tsp + cudagraph (#4871) ... * support qwen3_moe tsp mode * fix * fix * update * update * update * fix * support external_rmsnorm * update * fix	2025-11-10 23:37:51 +08:00
Neil Zhu	6de1ce3b25	[Metax] support ERNIE-4.5-VL-28B (#4820)	2025-11-07 04:55:49 -08:00
ming1753	cba185f1fe	[Feature] Optim PaddleOCR-VL (#4873) ... * [Feature] Optim PaddleOCR-VL * fix bug	2025-11-07 14:56:44 +08:00
Haonan Luo	79e6bf4bdc	[Others] Delete PaddleOCR Useless Function (#4815) ... * fix paddleocr prefix cache bug * add test for paddleocr_vl * disable prefix-caching in ocr * add test for paddleocr_vl * Fix top_p for rejection sampling * delete useless func for paddleocr --------- Co-authored-by: ming1753 <ideaminghp@163.com> Co-authored-by: ming1753 <61511741+ming1753@users.noreply.github.com>	2025-11-07 11:14:41 +08:00
YuBaoku	fa28745f19	[CI] Update ERNIE-4.5-VL baseline to adapt to MoE changes (#4867)	2025-11-06 22:02:10 +08:00
Jiang-Jia-Jun	6b68c58e8d	Revert "[Bug Fix] fix ernie4_5_vl_moe (#4843)" (#4863) ... This reverts commit 6460d4df27.	2025-11-06 19:18:29 +08:00
LokeZhou	6460d4df27	[Bug Fix] fix ernie4_5_vl_moe (#4843) ... * fix ernie4_5_vl_moe * fix vl moe meta	2025-11-06 19:16:33 +08:00
zhupengyang	b54eb7ad81	[XPU] ep+tp all2all (#4836)	2025-11-06 17:26:14 +08:00
Echo-Nie	c18b177f21	fix the get_act_fn,_load_st_projector (#4824)	2025-11-06 16:13:35 +08:00
Ayakouji	831266da7a	[Fix] fix ernie4_5_vl model torch format loadding (#4447) ... * fix * add test * fix test * fix test * update	2025-11-06 14:34:21 +08:00
K11OntheBoat	62dfad4a5f	[PD Disaggregation] Support Qwen3-MoE use PD + EP inference. (#4691) ... support Qwen-MoE PD/EP	2025-11-06 10:32:15 +08:00
kxz2002	9676cc87d6	fix parser register name (#4795) ... Co-authored-by: luukunn <83932082+luukunn@users.noreply.github.com>	2025-11-05 11:27:30 +08:00
zhupengyang	2fd254e5b7	support ep+tp at op layer (#4688)	2025-11-05 11:15:57 +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
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
ming1753	7681375a19	[BugFix] PaddleOCR-VL fix FD_DEBUG type and support v1 loader (#4605) ... * [Bug Fix] PaddleOCRVL fix FD_DEBUG type and support HF model * fix bug * fix bug * fix bug	2025-10-28 09:47:47 +08:00
CSWYF3634076	acd331780c	[V1 loader] Qwen25 VL support v1 loader and torch style safetensors load (#4388) ... * [BugFix] qwen2.5vl enable_thinking=true and image_patch_id bug fix * [Docs]offine infer add apply_chat_template add_generation_prompt parameter * [Model]qwen2.5VL support --use-cudagraph * [Model]qwen2.5VL support --use-cudagraph buffer and qwenvl test * [Model]qwen2.5VL support --use-cudagraph buffer and qwenvl test * [Model]qwen2.5VL support --use-cudagraph buffer and qwenvl test v2 * [Model]qwen2.5VL support --use-cudagraph buffer and qwenvl test v3 * [Model]qwen2.5VL support --use-cudagraph buffer and qwenvl test v4 * [Model]qwen2.5VL support --use-cudagraph buffer and qwenvl test v5 * [Model]qwen2.5VL support --use-cudagraph buffer and qwenvl test v6 * [Model]qwen2.5VL support --use-cudagraph buffer and qwenvl test v7 * qwen25vl v1 loader * qwen25vl v1 loader v2 * qwen25vl v1 loader v3 * qwen25vl v1 loader fix tp2 weight PySafeSlice * qwen25vl v1 loader no test * qwen25vl v1 loader add unit test * qwen25vl v1 loader add unit test v2 * qwen25vl v1 loader add torch unit test v3 * qwen25vl v1 loader add torch unit test v4 * qwen25vl v1 loader add torch unit test v5 * qwen25vl v1 loader add torch unit test v6	2025-10-27 10:54:15 +08:00
ming1753	e4e3cede7f	[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>	2025-10-24 23:34:30 +08:00
JYChen	83d45af1f3	fix import image_ops error on some platforms (#4559)	2025-10-24 16:09:20 +08:00
xiaozude	f7069b8057	[Metax] adapt DeepSeek (#4498)	2025-10-24 10:14:53 +08:00
YuanRisheng	ac4f5ca272	delete useless code (#4544) ... Co-authored-by: root <root@yqlcc01-sys-rpm12rzmwjd.yqlcc01.baidu.com>	2025-10-23 13:40:34 +08:00
Yuanle Liu	cef3164c3b	Optimizing the performance of think length limit using custom operators (#4279) ... * delete impl * delete min_length&max_length * support limit thinking content strategy * fix * fix * fix * update * fix set_value_by_flags_and_idx * fix * fix * fix * fix * update * fix * fix * fix typo * fix ci * fix * fix * support mtp * fix * fix * update * update	2025-10-20 21:09:13 +08:00