3129 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Zero Rains	e37e86b3b8	[V1 Loader]support param create and load for wint2 and xpu backend (#3581) ... * support wint2 backend' * [V1 Loader]support param create and load for wint2 and xpu backend * update weight shape name * update * update * update baseline.txt * update model name * update baseline.txt * fix codestyle * remove debug coode	2025-08-28 09:49:36 +08:00
lizexu123	b28a0343a6	fix ENABLE_V1_KVCACHE_SCHEDULER (#3625) ... Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>	2025-08-27 21:21:29 +08:00
ltd0924	2974016103	[BugFix] fix ce bugs (#3641) ... * [BugFix] fix tp8 client refuse * fix engine port bug * Update utils.py	2025-08-27 20:38:15 +08:00
Yuanle Liu	836345a4dd	delete ernie4_5_vl_tokenizer (#3631)	2025-08-27 20:36:02 +08:00
Liumengyuan	11803e0907	fix undefined cuPointerGetAttribute symbol error (#3628)	2025-08-27 20:24:59 +08:00
Jiang-Jia-Jun	c694fa2879	Revert "[Feature] block sparse attention (#3209)" (#3647) ... This reverts commit 646a0c2fd8.	2025-08-27 17:35:04 +08:00
李泳桦	b2afdf4fc6	[fix] qwen output inconsistency when top_p=0 (#3634) ... * [fix] qwen output inconsistency when top_p=0 * [fix] remove decode pre_id code	2025-08-27 17:16:23 +08:00
lzy	1265f6c192	deepgemm don't support tp+ep (for ci) (#3638) ... * deepgemm don't support tp+ep (for ci) * deepgemm don't support tp+ep (for ci)	2025-08-27 16:39:19 +08:00
plusNew001	f0140be1e1	Change paddlepaddle-xpu installation command (#3646) ... Updated the installation command for paddlepaddle-xpu to use a specific wheel file.	2025-08-27 16:17:19 +08:00
JYChen	e645db348b	[docs] Update best practice doc (#3539) ... * fix some docs error * [docs] x1 best-practice * update docs * fix docs	2025-08-27 15:45:30 +08:00
xjkmfa	afb9f327ef	【CI case】for echo finish_reason text_after_process and raw_prediction check (#3630) ... * Add ci case for min token and max token * 【CI case】include total_tokens in the last packet of completion interface stream output * echo&finish_reason&text_after_process&raw_prediction check * echo&finish_reason&text_after_process&raw_prediction check * echo&finish_reason&text_after_process&raw_prediction check * echo&finish_reason&text_after_process&raw_prediction check * echo&finish_reason&text_after_process&raw_prediction check --------- Co-authored-by: xujing43 <xujing43@baidu.com>	2025-08-27 15:21:16 +08:00
chen	5ad8721506	check (#3639)	2025-08-27 14:32:13 +08:00
plusNew001	f8b70bf60c	update xpu ci (#3632) ... * Update Docker image version in CI workflow * Modify paddlepaddle-xpu installation and add dependencies Updated installation source for paddlepaddle-xpu and added dependency download step. * Fix no_proxy environment variable in CI workflow	2025-08-27 14:25:56 +08:00
chen	ce9c0917c5	[Precision] Support lm_head layer running in float32 (#3597) ... * support lm_head fp32 bf16 fp16 * support lm_head fp32 bf16 fp16 * add doc and check code * lm_head_fp32 specify lm_head as fp32 * code check * check doc	2025-08-27 11:34:53 +08:00
xiaoxiaohehe001	ad319a87cc	support fa3 rope3d (#3622)	2025-08-27 11:31:29 +08:00
YUNSHEN XIE	85afa72763	fix publish task (#3635) ... * fix publish task * disable ut	2025-08-27 11:14:53 +08:00
yangjianfengo1	646a0c2fd8	[Feature] block sparse attention (#3209) ... * 支持稀疏attn * fix bug * code style * fix moba attn get kv shape * 修复a100编译 * codestyle * code style * code style * code style * fix conflict * 增加单侧 * code style * 增加eblite 加载时间 * fix bug * for ci * for ci * for ci * for ci * 支持mlp block size 128 * 增加小算子单测 * fix 单测 mlp * 将环境变量加入到config里面 * fix rollout config	2025-08-26 07:16:04 -07:00
RAM	f0a362af18	[CUDAGraph]Switch the scope so that output buffer of CUDAGraph can automatically release (#3612) ... * fix typo * fix typo * add print dot files * fix bug * Switch the scope so that output buffer of cudagraph can automatically release * Revert "add print dot files" This reverts commit dc21809eb5.	2025-08-26 21:28:19 +08:00
gaoziyuan	82e64b13e1	[NewFeature]Support dp multi api server && Fix some bug in mixed ep && merge develop (#3598) ... * [Feature] update ep * fix ci * fix ci * fix ci * fix ci * fix ci * fix ci * fix ci * fix queue ports idx * fix ci * fix ci * fix ci * fix ci * fix ci * fix ci * fix ci * fix ci * Update engine.py * fix ci * fix some bug in mixed ep * add server fix and op fix * rm some log * fix code style * ltd fix * fix * fix * fix some bug * fix bug * fix bug * fix style * Update config.py * Update splitwise_connector.py * Update cache_messager.py * Update __init__.py * merge and fix * Update engine.py * Update common_engine.py * Update run_ci_xpu.sh * Update ernie_processor.py * Update ernie_processor.py --------- Co-authored-by: ltd0924 <ltd0924@sina.com> Co-authored-by: ltd0924 <32387785+ltd0924@users.noreply.github.com>	2025-08-26 19:59:02 +08:00
Yuanle Liu	cbce94a00e	rename ernie_xxx to ernie4_5_xxx (#3621) ... * rename ernie_xxx to ernie4_5_xxx * ci fix	2025-08-26 19:29:27 +08:00
YuanRisheng	642480f5f6	[CI] Standard unittest (#3606) ... * standard unittest * fix bugs * fix script	2025-08-26 19:03:11 +08:00
SunLei	2f28f40d90	fix: replace list * n initialization with list comprehension to avoid shared references (#3618)	2025-08-26 17:53:31 +08:00
bukejiyu	3200a80de3	[v1 loader]support fp8 (#3593) ... * support fp8 * update ci	2025-08-26 02:42:46 -07:00
RAM	00898603c8	[CUDAGraph]Add debug func (#3616) ... * add print dot files * refine code	2025-08-26 16:43:48 +08:00
xiaoxiaohehe001	9afa236e39	[NewFeatures] support eplb (#3547) ... * [NewFeatures] support eplb * fix eplb	2025-08-26 16:19:30 +08:00
Yuanle Liu	56e2d7e668	adaptive rms_norm's dtype (#3617) ... * adaptive rms_norm's dtype * adaptive rms_norm's dtype * add approve coverage --------- Co-authored-by: liuyuanle <liuyuanle@baidu.com>	2025-08-26 15:29:15 +08:00
lzy	d339df2e90	Supports DP+TP+EP hybrid parallel deployment strategy (#3489) ... * Support DP+TP+EP hybrid parallel deployment strategy * Support DP+TP+EP hybrid parallel deployment strategy * fix conflict * add moe_tp_ep function split_allgather_out * del tp_group in moe_cutlass_backend * for ci * fix parallel_config for ci * del log	2025-08-26 00:04:01 -07:00
freeliuzc	52eda7fdb3	[Feature][MTP]support new speculative decoding method named hybrid mtp with ngram (#3610)	2025-08-26 14:29:22 +08:00
AIbin	0a0d2959b9	qkv_a_proj horizontal fusion (#3591) ... Support DSK qkv_a_proj horizontal fusion under V0 Loder	2025-08-26 14:25:57 +08:00
YuBaoku	75db0d1ae2	[CI] reopen sot test (#3613) ... * [CI] change check_service time to 360s * [CI] disable sot test temporarily * [CI] reopen sot test	2025-08-26 14:23:38 +08:00
xiaoxiaohehe001	70c75798a7	[NewFeatures] support noex rope3d (#3542) ... * [NewFeatures] support noex rope3d * [NewFeatures] support noex rope3d encoder	2025-08-26 11:44:57 +08:00
tianlef	0bc7d076fc	[CE]add x1 w4a8c8 benchamrk config (#3607) ... * [CE]add x1 w4a8c8 benchamrk config * [CE]add x1 w4a8c8 benchamrk config * [CE]add x1 w4a8c8 benchamrk config	2025-08-26 11:27:32 +08:00
Ryan	a5b4866ff1	[CudaGraph][SOT] Add unit tests for splitting the static graph into piecewise graphs that support cuda_graph (#3590) ... * add unitest * change sot_warmup_sizes * wtf; add missed commit	2025-08-26 11:25:04 +08:00
Sunny-bot1	c68c3c4b8b	[Feature] bad words support v1 scheduler and specifiy token ids (#3608) ... * support bad_words_token_ids * docs * fix test * fix * bad words support kvcache v1 and token ids * fix	2025-08-25 20:14:51 -07:00
lizexu123	c43a4bec00	[Features] support hugging face qwen3 dense and qwen2 model (#3574) ... * support qwen2 and qwen3 hugging face * fix moe * defualt_v1 loader * hugging_face_format deprecated * modify hugging_face_foramt to model_format * model_format auto * fix environemt * fix bug * fix qwen3-0.6 bug * model_format is str * fix	2025-08-26 10:54:53 +08:00
ltd0924	66c5addce4	[Bugfix] fix api server control signal bugs (#3531) ... * Update serving_chat.py * Update serving_completion.py * Update serving_completion.py	2025-08-25 21:13:04 +08:00
RAM	2fa173e327	[Executor] CUDAGraph support RL training (#3265) ... * add clear graph opt backend * cuda graph support rl * add branch * 1.fix dynamic_weight_manager bug 2.add clear api for CasualLM * open test case * fix typo * update mkdocs.yaml * [Docs]Update mkdocs.yml * update test case * use unittest in graph test case	2025-08-25 20:59:30 +08:00
Kane2011	2ae7ab28d2	[MetaxGPU] adapt to the latest fastdeploy on metax gpu (#3492)	2025-08-25 17:44:20 +08:00
YuBaoku	c13c904971	[CI] temporarily disable sot test due to occasional timeout issue (#3586) ... * [CI] change check_service time to 360s * [CI] disable sot test temporarily	2025-08-25 14:34:27 +08:00
chen	9cab3f47ff	[Feature] Add temp_scaled_logprobs and top_p_normalized_logprobs parameters for logits and logprobs post processing (#3552) ... * [feature] Add temp_scaled_logprobs and top_p_normalized_logprobs parameters for logits and logprobs post processing * infer engine support temp_scaled_logprobs and top_p_normalized_logprobs * delete some code * code check * code check and add doc * fix tokenizer.decoder(-1), return 'Invalid Token' * add ci for temp_scaled and top_p logprobs * check test * check seq len time shape * logprob clip inf --------- Co-authored-by: sunlei1024 <sunlei5788@gmail.com>	2025-08-25 14:11:49 +08:00
YUNSHEN XIE	2410adb041	Add coverage skip (#3553) ... * add coverage skip * update * fix	2025-08-25 14:08:24 +08:00
Yuan Xiaolan	9205c88da1	support w4afp8 EP inference (#3044)	2025-08-25 11:27:45 +08:00
YUNSHEN XIE	46664985fc	Modify the existing coverage collection method (#3573) ... fix cov report	2025-08-25 10:35:35 +08:00
YuBaoku	7821534ff5	[CI] add sot test (#3579) ... * [CI] add sot test * [CI] add sot test	2025-08-25 10:14:50 +08:00
lengxia	137e539456	[Feature][XPU] add custom kernels for mtp (#3537)	2025-08-25 10:14:17 +08:00
bukejiyu	bdbac0aa3d	support qwen2 weight only (#3571)	2025-08-24 11:14:34 +08:00
bukejiyu	77514e3e1e	[V1 Loader] support weight_only (#3413) ... * support wint4/wint8 * delete smoe case * update ci * print log	2025-08-23 13:13:41 +08:00
Jiang-Jia-Jun	93e1b63200	Revert "[UnitTest][Copilot] Improve unit test coverage for entrypoints module…" (#3564) ... This reverts commit 36325e9ea7.	2025-08-23 10:44:23 +08:00
YuanRisheng	e481b7a779	fix sot (#3556)	2025-08-23 08:37:06 +08:00
Zero Rains	79f0dbbb55	[V1 Loader] Support qwen2(bf16) (#3502) ... * support qwen2(bf16) * merge bias_loader and weight_loader	2025-08-23 01:08:23 +08:00