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
Yuanle Liu
2f74e93d7e
use dist.all_reduce(min) to sync num_blocks_local ( #2933 )
...
* pre-commit all files check
* reduce min num_blocks_local
* fix nranks=1
* pre-commit when commit-msg
2025-07-21 01:23:36 -07:00
lizexu123
67990e0572
[Feature] support min_p_sampling ( #2872 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* Fastdeploy support min_p
* add test_min_p
* fix
* min_p_sampling
* update
* delete vl_gpu_model_runner.py
* fix
* Align usage of min_p with vLLM
* fix
* modified unit test
* fix test_min_sampling
* pre-commit all files
* fix
* fix
* fix
* fix xpu_model_runner.py
2025-07-20 23:17:59 -07:00
周周周
8c5407d9e4
remove cum_offsets from ForwardMeta ( #2925 )
Deploy GitHub Pages / deploy (push) Has been cancelled
2025-07-19 23:57:27 +08:00
Zero Rains
25698d56d1
polish code with new pre-commit rule ( #2923 )
2025-07-19 23:19:27 +08:00
ming1753
5328daa333
[Bug Fix] fix ep config bug ( #2920 )
2025-07-18 19:12:56 +08:00
xiaoxiaohehe001
a42fc3f40b
[Feature] Support 45tVL EP FP8 Infer. ( #2909 )
...
* support_mm_ep_fp8
* support_mm_ep
2025-07-18 17:57:15 +08:00
gaoziyuan
6efad14b95
support vl ori_vacab_size ( #2900 )
2025-07-18 16:26:14 +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
freeliuzc
d49f8fb30a
[Feature][MTP] Support cacheKV transfer in per_chunk mode ( #2890 )
...
* support chunk_prefill both normal and speculative_decoding(mtp)
* optimize pd-disaggregation config
* fix bug
2025-07-17 17:58:08 +08:00
Yuanle Liu
dbb9e2506b
Fix rollout_model init ( #2881 )
2025-07-16 22:36:21 -07:00
ming1753
1f15ca21e4
[Feature] support prompt repetition_penalty ( #2806 )
Deploy GitHub Pages / deploy (push) Has been cancelled
2025-07-17 12:05:52 +08:00
Yuanle Liu
63d6e7ce06
fix and refine vl ( #2866 )
...
* refine vl config
* delete attn_sep
* fix vl accuracy
2025-07-16 05:59:28 -07:00
周周周
aa76085d1f
[Attention] remove cum_offsets from atten, and use cu_seqlens_q ( #2870 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
[Attention] remove cum_offsets from atten, and use cu_seqlens_q (#2870 )
2025-07-16 20:10:57 +08:00
Yuanle Liu
dda4a9f848
rl update ( #2861 )
2025-07-16 00:33:10 -07:00
xiaoxiaohehe001
0d0340392f
[Fix] Fix mm ep weight init. ( #2855 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* fix_45t_mm
* Update load_weight_utils.py
* Update load_weight_utils.py
2025-07-16 12:02:39 +08:00
freeliuzc
2d1184aefe
[Fix] fix expert_parallel bug in decoder stage ( #2848 )
2025-07-16 11:08:18 +08:00
RAM
0fad10b35a
[Executor] CUDA Graph support padding batch ( #2844 )
...
* cuda graph support padding batch
* Integrate the startup parameters for the graph optimization backend and provide support for user - defined capture sizes.
* Do not insert max_num_seqs when the user specifies a capture list
* Support set graph optimization config from YAML file
* update cuda graph ci
* fix ci bug
* fix ci bug
2025-07-15 19:49:01 -07:00
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
Zero Rains
e7bcbbab52
Merge vl execution path into normal execution path ( #2829 )
...
* merge vl model into gpu_model runner
Change-Id: I9f4691a3d5f135e8d72b1d58abcd15ef3aa3f2a6
* fix chinese
Change-Id: Ic7405109b984c21e076fb3b01ff6feb571d0119a
* fix the parse parameter
Change-Id: I4cd62ee87c06220af580d91e347145d4394917fe
* fix the bug in online_inference
Change-Id: Idb111bb2114e83017c4050b2a68cf039c6d3c559
* polish code
Change-Id: I7d4194102c2f1b0743b74fbd5fc284eb8ef4d17c
2025-07-15 22:20:03 +08:00
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
freeliuzc
7cdd8d290d
[MTP] optimize mtp infer speed ( #2840 )
Deploy GitHub Pages / deploy (push) Has been cancelled
2025-07-14 19:50:22 +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
freeliuzc
7f64d408a9
[MTP] support expert-parellel in mtp ( #2835 )
2025-07-14 14:28:50 +08:00
bukejiyu
bad53c6b6e
[vl]remove duplicated load logic ( #2744 )
Deploy GitHub Pages / deploy (push) Has been cancelled
2025-07-13 07:36:26 +08:00
gaoziyuan
749b2e9c89
support qwen3moe name_mapping ( #2820 )
2025-07-12 12:05:54 +08:00
zhink
c08561c13a
[Feature] support tensor-parallel-size>num_key_value_heads for qwen3 ( #2799 )
2025-07-11 15:09:43 +08:00
Sunny-bot1
240d6236bc
[Fix]fix top_k_top_p sampling ( #2801 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* fix topk-topp
* update
* add base_non_truncated
2025-07-10 22:35:10 +08:00
littledgg
59071268b6
[Executor] Move forward_meta.py to fastdeploy/model_executor ( #2774 )
...
* Use PEP 563 in attention.py and fix conflict
* merge commit
* Change what was left out last time
2025-07-10 20:36:51 +08:00
lizexu123
8c660a0dfb
[BugFix] fix RMSNorm rms_norm_esp ( #2797 )
...
* fix rms
* add vl
* fix
* add vl
* fix
* fix
2025-07-10 20:02:24 +08:00
chen
d33105baeb
[Feature] Online Chat API Support Return logprobs ( #2777 )
...
* online chat support logprobs
* check xpu
* check vl_gpu_model_runner and xpu_model_runner
* get_worker() check platform
2025-07-10 16:33:40 +08:00
K11OntheBoat
24f934f1f9
[BugFix] Fix low prediction accuracy of deepseekv3 ( #2798 )
2025-07-10 16:16:44 +08:00
Sunny-bot1
1e2319cbef
Rename top_p_sampling to top_k_top_p_sampling ( #2791 )
2025-07-10 00:09:25 -07:00
Sunny-bot1
e45050cae3
[Feature] support top_k_top_p sampling ( #2753 )
...
* support top_k_top_p sampling
* fix
* add api param
* add api para
* fix
* fix
* fix
* fix
* fix
* fix
* fix
2025-07-09 20:58:58 -07:00
Ryan
b0f525955c
[SOT] Remove breakgraph in post processing && fix datatype ( #2780 )
2025-07-10 11:26:00 +08:00
chen
888780ffde
[Feature] block_wise_fp8 support triton_moe_backend ( #2767 )
2025-07-09 19:22:47 +08:00
RAM
e3768c5a83
[Executor] Fix bug of logger.debug ( #2778 )
2025-07-09 04:13:43 -07:00
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
RAM
03a74995b8
Clear dead code And supplementary notes ( #2757 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* 1.supplementary notes 2.delete dead code
* fix bug of forward meta
* Global modification of forward meta
* fix vl model_runner bug
2025-07-09 16:17:34 +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
Ryan
c4718fd693
Enable SOT D2St in Multimodal Model ( #2735 )
2025-07-09 12:26:18 +08:00
GoldPancake
f7cad30a38
[Feature] Add speculative decoding simulation benchmark. ( #2751 )
...
* Add speculative decoding simulation benchmark
* Fix the name of the parameter
2025-07-09 12:08:43 +08:00
RichardWooSJTU
6610aa29d0
Revert "[Bug fix] fix attention rank init ( #2743 )" ( #2761 )
...
This reverts commit e8bbe7244b
2025-07-09 10:38:12 +08:00
Ryan
f72c4de539
[SOT] Make custom_op dy&st unified ( #2733 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* make_custom_op dy&st unified
* add instance judgement
2025-07-08 19:21:44 +08:00
RichardWooSJTU
e8bbe7244b
[Bug fix] fix attention rank init ( #2743 )
...
* fix attention rank init
* fix attention rank init
2025-07-08 17:19:49 +08:00
lizexu123
525be243e7
[Bug fix] Fixed the garbled text issues in Qwen3-8B ( #2737 )
...
* fix qwen3.py
* update
* update lm_head tie_word_embeddings
* update tie_word_embeddings
* fix
* fix tie_word_embedding not in config.json
---------
Co-authored-by: lizexu <lizexu@baidu.com >
2025-07-07 23:15:27 -07:00
EnflameGCU
d0f4d6ba3a
[GCU] Support gcu platform ( #2702 )
...
baseline: e7fa57ebaexing.wo@163.com >
2025-07-08 13:00:52 +08:00
