58 Commits

Author	SHA1	Message	Date
YuBaoku	819b2dbbae	Revert "【New Feature】W4afp8 supports per group quantization (#4272)" (#4854) ... This reverts commit 93fcf7e4ec.	2025-11-06 17:48:28 +08:00
yangjianfengo1	93fcf7e4ec	【New Feature】W4afp8 supports per group quantization (#4272) ... * w4afp8 支持per group * code style * 精度完成 * revert append attn utils * ffn1 动态量化 * ffn2 支持动态量化 * code style * code style * 修改单测 * 修改单测 * fix bug * Implement conditional parameter creation for layers Add parameter creation for up_gate_proj_in_scale when ep_size > 1. * code style * fix conflict * code style * code style * 修复w4aint8 精度 * fix ci --------- Co-authored-by: yuanxiaolan <yuanxiaolan01@baidu.com>	2025-11-05 21:00:23 +08:00
周周周	937eb3c6ed	[get_padding_offset.] clean get_padding_offset.cu (#4777) ... [get_padding_offset.] clean get_padding_offset.cu (#4777)	2025-11-05 10:47:40 +08:00
freeliuzc	11398790d3	[Speculative Decoding][MTP]Support attn mask offset (#4641) ... * [MTP]Merge support attn (#4591) * support mask_offset in speculate decoding * fix dummpy run output * add unit test * fix unit test import * support attn_mask_offset in mtp mode * add update_attn_mask op * fix unit test && fix code-style	2025-11-03 10:08:01 +08:00
Yuanle Liu	b301bd6c31	[BugFix] fix thinking bug (#4710) ... * fix thinking bug * fix ut * update * fix	2025-10-31 22:00:31 +08:00
GoldPancake	1f3ce65b58	[Feature] support mtp distribution equivalence verification (#4699)	2025-10-31 11:45:04 +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
Lucas	5c6105f4a2	[XPU] bind some OPs for VL model with pybind (#4522)	2025-10-27 10:50:08 +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
GoldPancake	47595a2480	[Feature] support mtp logprob (#4464) ... * support mtp logprob * fix unitest	2025-10-20 15:18:12 +08:00
Haonan Luo	1b9f351d21	Support GPT-OSS-BF16 (#4240) ... * [Feature] AppendAtten support sinks & HEAD_DIM=64 * fix bug * fix bug * fix bug * fix bug * [Feature] support gpt-oss * fix bug * add mask * support-gpt-oss * support-gpt-oss * fix long seq * support wint8 * support wint8 * support wint8 * update test * change sliding windows init pos --------- Co-authored-by: ming1753 <ideaminghp@163.com> Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com> Co-authored-by: ming1753 <61511741+ming1753@users.noreply.github.com>	2025-10-20 14:44:58 +08:00
yzwu	4b661512ca	[Iluvatar GPU] Adapt VL model (#4313)	2025-10-17 16:13:38 +08:00
Ryan	49cea8fb1c	[SOT][Cudagraph] Remove BreakGraph of #3302 && update CustomOp (#3694) ... * rm inplace info && to(gpu) * update append_attention * unpin paddle version * add full_cuda_graph=False * add blank line --------- Co-authored-by: SigureMo <sigure.qaq@gmail.com>	2025-10-17 10:57:55 +08:00
freeliuzc	582aebd48b	[MTP]support mtp chunk_prefill_v1 (#4366) ... * support mtp chunk_prefill_v1 * fix mtp chunkprefill output, fix unit test * fix unit test * fix save_output	2025-10-15 13:21:32 +08:00
Sunny-bot1	a751d977bc	[Optimization] Fuse get_max_len and get_kv_max_len (#4369) ... * opt split_q_block * fuse max_lens and max kv_len	2025-10-13 20:35:00 +08:00
RAM	aa27b03bc0	[Executor]CUDAGraph support Speculate Decode (#3769) ... * success run ngram * Revert "[Code Simplification] remove cum_offsets (#3410)" This reverts commit 32b39620bc. * success run ngram5 tp4 42bs * success run ngram5 tp4 42bs * mtp draft commit * add decorator for target model * enable draft model in cudagraph v0.5 * revert revrt cum_offset * enable target model in cudagraph v0.9 And clean debug code * Revert "success run ngram" This reverts commit 8351e83993. * add reverted code * enable target model in cudagraph v0.9 * solve comment * fix bid < 0 * Enable Target Model Padding And Draft Model in cudagraph * solve problem * delete rebuild padding debug note * fast compile * Add capture list for mtp * success run 256 tp1 mtp * Enable Lite TP2 Bsz256 * realy enable tp2 bsz 256 * fix problem * Solve problem for Draft model in cudagraph * Solve comment * replace emptytensor as zeros * Solve comments * Revert "fast compile" This reverts commit 834639a7ff. * fix bug * fix merge bug * fix typo * fix bug --------- Co-authored-by: lizexu <2694294196@qq.com> Co-authored-by: littledgg <1658565283@qq.com> Co-authored-by: zeroRains <linjunlu@zerorains.top> Co-authored-by: gongshaotian <gstain5555@outlook.com>	2025-10-09 21:18:29 +08:00
chen	81959c7d88	[NewFeature]custom_allreduce support cudagraph recapture (#4305) ... * custom_allreduce support cudagraph recapture * add shut_down/restart default group	2025-09-29 15:56:54 +08:00
chen	1a6283424e	Fix noaux_tc cuda Error 700 in CUDAGraph (#4174)	2025-09-23 18:41:33 +08:00
AIbin	a7392a0ff9	【Inference Optimize】DeepSeek-V3-model MLA Optimize (#3886) ... * support MLA chunk_size auto search & cuda_graph	2025-09-11 10:46:09 +08:00
Ayakouji	453487d5b0	[Feat] ernie4_5_vl_moe support CudaGraph (#3226) ... * delete dynamic control flow for decode * coda-style * fix scatter/gather typos and use input stream instead default stream * support 0-Size Tensor * update runner and model * using static mem address as input * fix mem leak * refine code * update mm_buffer * fix typo * fix buffersize * fix unk token * refine code * refine * support other arch * open cudagraph in vlci * fix * update * update * update * fix cmd * update --------- Co-authored-by: aquagull <hongyuh@qq.com> Co-authored-by: Yuanle Liu <yuanlehome@163.com>	2025-09-10 13:11:57 +08:00
Jundong Liu	3d0aaa5923	[Excutor] Experiment Feature-Support Prefill in cudagraph (#3459) ... * Support prefill in Cudagraph * Refactor GetBlockShapeAndSplitKVBlock Kernel V2 * Refactor GetBlockShapeAndSplitKVBlock Kernel V2.1 * Refactor GetBlockShapeAndSplitKVBlock Kernel V2.2 * Refactor GetBlockShapeAndSplitKVBlock Kernel V2.3 * Refactor GetBlockShapeAndSplitKVBlock Kernel V2.4 * Refactor GetBlockShapeAndSplitKVBlock Kernel V2.5 * Solve problem about encoder_num_blocks_x_cpu * Add early-exit mechanism for attention kernel * fix test case about append-attention * Update testcode, Add annotations to related tensors * move get_input_length_list * solve test_code * Add annotations about early-exit for attention kernel * Add annotations about early-exit for attention kernel2 * solve comment * solve mtp --------- Co-authored-by: RAM <gstian5555@outlook.com>	2025-09-08 13:12:24 +08:00
Yuan Xiaolan	2cf55168ca	load hadamard_block_size from config (#3797)	2025-09-05 17:07:58 +08:00
freeliuzc	88d44a2c93	support mtp in v1_scheduler mode (#3695)	2025-09-04 17:39:59 +08:00
co63oc	5441538173	rename fused_get_rope.cu (#3752) ... * rename fused_get_rope.cu * fix * fix typos * fix * fix	2025-09-03 10:54:34 +08:00
co63oc	d6369b4d51	fix typos (#3684)	2025-09-01 17:50:17 +08:00
Sunny-bot1	fe5d09f9ee	[FIX]Fix Machete compile via ENABLE_MACHETE (#3727) ... * add ENABLE_MACHETE * fix * revert * update * pre_commit * fix * fix --------- Co-authored-by: Ayakouji <yuhongh@qq.com> Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com> Co-authored-by: aquagull <hongyuh@qq.com>	2025-08-30 17:50:17 +08:00
yangjianfengo1	3754a9906d	[Feature] block sparse attention (#3668) ... * 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 * 修复显存 * add test server * add test server * fix mlp 最后一层使用full attn	2025-08-29 19:46:30 +08:00
Liumengyuan	e93d4cfcdd	Add with_output version AppendAttention (#3302) ... * get use_output from fd_config * add clear TODO description * add mask_offset para to align with develop * fix bug * fix use_output logic * fix sot bug	2025-08-28 17:10:18 +08:00
yangjianfengo1	e81046fdad	【New Feature】集中式支持w4afp8 (#3644) ... * 支持tp w4afp8 * code style	2025-08-28 10:53:24 +08:00
Sunny-bot1	479c8b85d3	[Optimize]support machete weight only gemm (#3561) ... * support machete weight only gemm * add generate * update * fix * change file location * add sm_version limit * fix * fix * fix ci * fix coverage * fix xpu	2025-08-28 09:49:58 +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
xiaoxiaohehe001	ad319a87cc	support fa3 rope3d (#3622)	2025-08-27 11:31:29 +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
freeliuzc	52eda7fdb3	[Feature][MTP]support new speculative decoding method named hybrid mtp with ngram (#3610)	2025-08-26 14:29:22 +08:00
Yuan Xiaolan	9205c88da1	support w4afp8 EP inference (#3044)	2025-08-25 11:27:45 +08:00
Ryan	bcdfc1d6b9	Add custom op declaration for all_reduce (#3473) ... * add custom op declaration * roll back try except	2025-08-20 20:29:58 +08:00
freeliuzc	a12d0bc549	[Feature][MTP]update multi-draft-token strategy (#3369) ... * update multi-draft-token strategy * fix format --------- Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>	2025-08-18 13:59:56 +08:00
chen	f0f00a6025	[OPs] Universal optimization and Fix early_stop cuda 700 (#3375) ... * delete nonzero * delete setup_ops_base.py * check if * check gcp infer_seed.cpu() * fix repetition_early_stopper_kernel cuda 700	2025-08-14 22:40:44 +08:00
lzy	1e06b9fa6d	make append_attn supports mask_offset (#3138) ... * make append_attn supports mask_offset * add unittest	2025-08-14 03:40:55 -07:00
Yuan Xiaolan	7ce00e597c	support qk norm (#3145)	2025-08-05 16:46:14 +08:00
yangjianfengo1	64d7a3194d	集中式支持fa3 (#3112)	2025-08-01 18:03:36 +08:00
Ryan	94264bbf60	[Code Simplification] Refactor Post-processing in VL Model Forward Method (#2937) ... * rm sth useless * refactor model forward * mv bool index to kernel	2025-08-01 17:28:07 +08:00
RAM	d850660872	[Executor] Refactor GetBlockShapeAndSplitKVBlock Kernel (#2989) ... * reset decoder_block_shape_q buffer * refactor GetBlockShapeAndSplitKVBlock Kernel and cudagraph padding batch * update decode_max_tile_size * fix pre-commit * update block_multihead_attn_backend * update flas attn backend * update MLA Attention * update XPU Attention * update gcu,iluvatar model runner * Update MTP * fix MTP bug	2025-07-31 00:09:31 +08:00
JYChen	dafe02a7b9	[stop sequence] support stop sequence (#3025) ... * stop seqs in multi-ends * unittest for gpu stop op * kernel tid==0	2025-07-29 14:17:37 +08:00
xiaoxiaohehe001	2970b00dfa	[Feature] Support_eplb (#2997) ... * [Feature] support_eplb * [Feature] support_eplb * [Fix] fix mm ep	2025-07-24 20:22:45 +08:00
chenjian	85a78d695d	[Feature] Support block scheduler v1 for FD (#2928) ... * Support FD block scheduler v1 * Support FD block scheduler v1 * Support FD block scheduler v1 * Fix according to copilot review * Fix according to review * Remove is_dummy * Fix bug when real_bsz=1 * Fix infer first token cost time --------- Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>	2025-07-23 20:31:31 +08:00
GoldPancake	9b84d51e25	[MTP Fix] Fix code and register cpp operators (#2965)	2025-07-22 19:36:24 +08:00
周周周	d306944f4f	remove cum_offsets from get_block_shape_and_split_kv_block (#2913) ... * remove padding_offsets from get_padding_offset.cu * remove padding_offsets from get_padding_offset.cu * remove padding_offsets from get_padding_offset.cu * remove cum_offsets from get_block_shape_and_split_kv_block * remove cum_offsets from get_block_shape_and_split_kv_block	2025-07-18 16:13:32 +08:00
周周周	ddb10ac509	[Inference, rename] remove padding_offsets from atten use batch_id_per_token (#2880) ... * remove padding_offsets from atten	2025-07-17 18:41:31 +08:00
周周周	aa76085d1f	[Attention] remove cum_offsets from atten, and use cu_seqlens_q (#2870) ... [Attention] remove cum_offsets from atten, and use cu_seqlens_q (#2870)	2025-07-16 20:10:57 +08:00