Kane2011
b4fef2cf29
[MetaxGPU] Support FastDeploy on metax gpu ( #3241 )
...
* [MetaxGPU] Support FastDeploy on metax gpu
* Update metax_worker.py
1. change worker log;
2. remove custom allreduce, adapt it later;
3. remove cuda graph;
* Update __init__.py
1. remove metax's key work comment
* Update __init__.py
1. remove metax's key word comment;
2. add fused_moe_kernel_paddle import
---------
Co-authored-by: yongqiangma <xing.wo@163.com >
2025-08-13 11:11:54 +08:00
Zero Rains
42af0b4b64
[V1 Loader] Support DeepSeekV3(bf16) ( #3294 )
...
* Support new loader for DeepSeekV3(bf16)
* update paddle version
* remove useless attr
2025-08-11 13:39:28 +08:00
gaoziyuan
a799d14df1
[Bugfix] Fix model accuracy in some ops ( #3231 )
...
* fix noaux_tc op
* fix
* update
* fix qk norm
* fix linear for prequant loader
* test
* fix
* fix
* rm some print
* fix noaux_tc op
* test
* Fix the confused enable_early_stop when only set early_stop_config (#3214 )
* fix the confused early_stop_config when only set early_stop_config
* pre-commit
* write a general method
* Add ci case for min token and max token (#3229 )
Co-authored-by: xujing43 <xujing43@baidu.com >
* add some evil cases (#3240 )
* add repitation early stop cases
* add repitation early stop cases
* add bad cases
* add bad cases
* add evil cases
* qwen3_moe (#3084 )
* [Feature] support seed parameter (#3161 )
* support seed
* fix
* add SamplingMetadata seed test
* The next_tokens values are inconsistent!
* add air and rejection seed test
* fix
* add SamplingParams seed test
* fix seed=0
* Default to defualt
* fix
* fix args_utils
* fix review
* fix review
* fix
* fix
* add xpu,gcu,iluvatar support seed
* fix
* 【Fix Bug】 修复 fa3 支持集中式bug (#3235 )
* fix fa3 集中式bug
* 增加qknorm参数
* fix qk norm
* fix
* update
* fix linear for prequant loader
* fix
* fix
* rm some print
* fix
* fix moe init weight&scale
* fix moe init weight&scale
---------
Co-authored-by: bukejiyu <395822456@qq.com >
Co-authored-by: yuanxiaolan <yuanxiaolan01@baidu.com >
Co-authored-by: Zero Rains <linjunlu@zerorains.top >
Co-authored-by: xjkmfa <108254620+xjkmfa@users.noreply.github.com >
Co-authored-by: xujing43 <xujing43@baidu.com >
Co-authored-by: Divano <dddivano@outlook.com >
Co-authored-by: bukejiyu <52310069+bukejiyu@users.noreply.github.com >
Co-authored-by: lizexu123 <39205361+lizexu123@users.noreply.github.com >
Co-authored-by: yangjianfengo1 <125249383+yangjianfengo1@users.noreply.github.com >
Co-authored-by: qingqing01 <dangqingqing@baidu.com >
2025-08-08 17:30:37 +08:00
Zero Rains
ce1f353c70
Move create_parameters to __init__ in FuseMOE for CultassBackend and TritonBackend ( #3148 )
...
* w4a8 bug
* fix w4a8 bug
* remove code
* modify the triton backend
* fix ep
* fix the bug with tensor_wise_fp8 in triton backend
* fix the RL
* fix bug by merge
* fix the bug in w4a8
* fix the tensor_wise_fp8 bug
* fix RL
2025-08-08 15:55:47 +08:00
bukejiyu
20839abccf
qwen3_moe ( #3084 )
2025-08-06 14:45:27 +08:00
Yuan Xiaolan
af543b7f0f
revise get_moe_scores ( #3164 )
2025-08-05 16:43:07 +08:00
RichardWooSJTU
f5c64a074c
[EP] Refactor DeepEP Engine Organization for Mixed Mode & Buffer Management Optimization ( #3182 )
...
* Add support for mixed-ep across multi nodes
* code refine
---------
Co-authored-by: yuanxiaolan <yuanxiaolan01@baidu.com >
2025-08-05 15:40:11 +08:00
Yuan Xiaolan
1f8289e106
fix expertwise_scale ( #3181 )
2025-08-04 20:06:15 +08:00
Yuan Xiaolan
5f56d289a7
fix is_permuted ( #3098 )
...
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com >
2025-07-31 19:58:05 +08:00
Yuan Xiaolan
35935da9e5
support W4A8 EPLB ( #3075 )
2025-07-30 14:34:12 +08:00
Yuan Xiaolan
3214fb5393
support model loading for w4a8 offline quant ( #3064 )
...
支持W4A8 EP 对离线量化权重的load
2025-07-29 21:54:37 +08:00
Longzhi Wang
be0a0f2bb2
fix arguement error in ep when pd ( #3060 )
2025-07-29 17:17:24 +08:00
YuanRisheng
502ee92a0a
Unify server-side and model-side Config (Part3) ( #3047 )
...
* merge model config
* fix arch
* fix rl
2025-07-29 17:07:44 +08:00
Longzhi Wang
907d561523
fix ep when paddle version mismatch ( #3056 )
2025-07-29 15:06:49 +08:00
Yuan Xiaolan
b1d787a272
[fix] w4a8 model loading and hadamard config ( #3013 )
2025-07-28 18:17:59 +08:00
AIbin
ec52d39e68
【Inference Optimize】Update wint2 weight n-dim reorder ( #3042 )
2025-07-28 16:31:56 +08:00
Longzhi Wang
247010d298
fix arguement error ( #3030 )
2025-07-28 11:03:29 +08:00
Longzhi Wang
0700c90caa
[Feat] support mixed ep ( #2969 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* Support mixed ep
* fix comment
* fix comment
* update mixep
* fix conflict
* fix typo
* update
* fix typo
* fix code style
* fix conflict
2025-07-25 15:29:30 +08:00
xiaoxiaohehe001
2970b00dfa
[Feature] Support_eplb ( #2997 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* [Feature] support_eplb
* [Feature] support_eplb
* [Fix] fix mm ep
2025-07-24 20:22:45 +08:00
Zero Rains
0fb37ab7e4
update flake8 version to support pre-commit in python3.12 ( #3000 )
...
* update flake8 version to support pre-commit in python3.12
* polish code
2025-07-24 01:43:31 -07:00
bukejiyu
bfeb664ab8
update ( #2978 )
Deploy GitHub Pages / deploy (push) Has been cancelled
2025-07-24 00:16:42 +08:00
chen
ad202272ed
【Infer】Improve the performance block_wise_fp8 of triton_moe_backend ( #2942 )
2025-07-23 13:02:50 +08:00
K11OntheBoat
93bb68aa71
[Feature] Marlin MoE backend supports DeepseekV3 ( #2962 )
...
Co-authored-by: K11OntheBoat <“ruianmaidanglao@163.com ”>
2025-07-22 18:11:15 +08:00
lifulll
2c6a9e887e
native top_p_sampling ( #2901 )
2025-07-22 14:09:59 +08:00
zhink
0262ef7eb3
custom all reduce support cuda graph ( #2938 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* Support enabling cuda graph and custom all reduce at the same time, and fix the overwritten custom all reduce flag
* rename communication_op to communication
2025-07-21 22:52:03 +08:00
周周周
ff4569f135
remove some code in ep.py ( #2947 )
2025-07-21 22:44:57 +08:00
Zero Rains
25698d56d1
polish code with new pre-commit rule ( #2923 )
2025-07-19 23:19:27 +08:00
Yuanle Liu
dda4a9f848
rl update ( #2861 )
2025-07-16 00:33:10 -07:00
freeliuzc
2d1184aefe
[Fix] fix expert_parallel bug in decoder stage ( #2848 )
2025-07-16 11:08:18 +08:00
Yuanle Liu
61b3997b85
refactor rl get_name_mappings_to_training ( #2847 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* refactor rl get_name_mappings_to_training
* fix tp>1
* change variable name(ffn1->up_gate_proj/ffn2->down_proj)
* change variable name(linear_weight->weight/linear_bias->bias)
* add rl names mapping for vl
* fix ernie 0.3B error
* fix develop code
* fix
2025-07-15 07:31:42 -07:00
AIbin
fd91da7b41
【Inference Optimize】Support wint2 triton kernel about triton_utils_v2 ( #2842 )
...
* update supported_models doc
2025-07-15 14:35:40 +08:00
YuanRisheng
4c7b8bc458
Simplify the Config code ( #2770 )
...
* simplify the code
* fix vl
* delete config
* fix
* perfect code
* fix ci
* fix xpu
* fix xpu
* fix server
* resolve conflict
* fix mtp
* resolve conflict
* fix xpu
* fix xpu
* fix vl
* fix log
* fix qwen moe
* fix qwen moe
* fix qwen moe
2025-07-14 19:50:05 +08:00
chen
888780ffde
[Feature] block_wise_fp8 support triton_moe_backend ( #2767 )
2025-07-09 19:22:47 +08:00
lifulll
1f28bdf994
dcu adapter ernie45t ( #2756 )
...
Co-authored-by: lifu <lifu@sugon.com >
Co-authored-by: yongqiangma <xing.wo@163.com >
2025-07-09 18:56:27 +08:00
yulangz
be21ef5047
[XPU] Supports BF16 for ERNIE-4.5-21B-A3B and ERNIE-4.5-0.3B ( #2765 )
...
* fix no quant xpu moe
* change dir of xpu moe weight only
2025-07-09 15:57:51 +08:00
RichardWooSJTU
fee544e808
fix ep prefill ( #2762 )
2025-07-09 14:03:05 +08:00
EnflameGCU
d0f4d6ba3a
[GCU] Support gcu platform ( #2702 )
...
baseline: e7fa57ebaexing.wo@163.com >
2025-07-08 13:00:52 +08:00
gaoziyuan
26d5d737dd
【Fearture】support qwen2 some func ( #2740 )
...
* add rl qwen model support
* fix
* fix
2025-07-08 12:03:04 +08:00
ming1753
1eb8ea7328
[Bug fix] fix complie bug when sm < 89 ( #2738 )
2025-07-08 11:24:52 +08:00
ming1753
ef6649a577
[Optimize] Optimize tensorwise fp8 performance ( #2729 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* [Optimize] Optimize tensorwise fp8 performance
2025-07-07 20:06:28 +08:00
liddk1121
1b54a2831e
Adapt for iluvatar gpu ( #2684 )
2025-07-07 16:53:14 +08:00
Jiang-Jia-Jun
05c670e593
[Sync] Update to latest code ( #2679 )
...
* [Sync] Update to latest code
* Add new code files
* Add new code files
* update code
* Try to fix build.sh
* Try to fix build.sh
* Update code
* Update requirements.txt
* Update code
---------
Co-authored-by: Jiang-Jia-Jun <jiangjiajun@baidu.com >
2025-07-03 15:43:53 +08:00
AIbin
a197dcd729
【Inference Optimize】Support ERNIE-4_5-300B-A47B-2BITS-Paddle model TP2/TP4 Inference ( #2666 )
...
* Support TP2&TP4 Wint
* Support TP2&TP4 Wint2 Inference
2025-07-01 18:29:11 +08:00
Jiang-Jia-Jun
92c2cfa2e7
Sync v2.0 version of code to github repo
2025-06-29 23:29:37 +00:00
jiangjiajun
684703fd72
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
