Zero Rains
b2f9a42d87
[Feature] Support repetition early stop ( #3024 )
...
* support repetition early stop and support user to set the parameter
* remove log
* fix codestyle
* add the early_stop_config to rollout_config
* update config and EarlyStopper class
* fix the bug for triton
* modify the stop method
* update description
* modify the usage for stop_flags
---------
Co-authored-by: Yuanle Liu <yuanlehome@163.com >
2025-07-29 22:42:54 +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
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
Yuan Xiaolan
b1d787a272
[fix] w4a8 model loading and hadamard config ( #3013 )
2025-07-28 18:17:59 +08:00
K11OntheBoat
83048bbe55
[Feature] Deepseekv3 supports cudagraph ( #3041 )
...
Co-authored-by: K11OntheBoat <“ruianmaidanglao@163.com ”>
2025-07-28 17:12:54 +08:00
AIbin
ec52d39e68
【Inference Optimize】Update wint2 weight n-dim reorder ( #3042 )
2025-07-28 16:31:56 +08:00
YuanRisheng
bddf403576
Unify server-side and model-side Config (Part2) ( #3035 )
...
* merge speculative and graph opt conifg
* add attr
2025-07-28 15:31:48 +08:00
Longzhi Wang
247010d298
fix arguement error ( #3030 )
2025-07-28 11:03:29 +08:00
YuanRisheng
6ccc10ad47
Unify server-side and model-side Config (Part1) ( #3018 )
...
* move cache config
* fix mtp
2025-07-28 10:51:52 +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
chen
332154f504
[feature] Support FA2 ( #3009 )
2025-07-25 14:09:00 +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
littledgg
f37d00e856
[Model] Provide clearer error for missing KV cache quantization scales ( #3007 )
2025-07-24 20:15:00 +08:00
EnflameGCU
c40df1802e
[GCU] Update to develop ( #2988 )
2025-07-24 19:30:52 +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
xiaoxiaohehe001
2c0ff068e2
[Fix] fix mm ep empty run ( #2999 )
2025-07-24 14:15:55 +08:00
lizhenyun01
29c3292f02
support c4 attn && fix cache
2025-07-24 12:00:52 +08:00
lizexu123
832d25334a
[Code Simplification] fix init_distributed_environment() ( #2982 )
2025-07-24 11:43:28 +08:00
bukejiyu
bfeb664ab8
update ( #2978 )
Deploy GitHub Pages / deploy (push) Has been cancelled
2025-07-24 00:16:42 +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
chen
172e69fe17
FA3 fix bug ( #2987 )
2025-07-23 19:07:43 +08:00
lizexu123
9b22b8d2c3
delete max-len ( #2959 )
2025-07-23 15:11:39 +08:00
chen
ad202272ed
【Infer】Improve the performance block_wise_fp8 of triton_moe_backend ( #2942 )
2025-07-23 13:02:50 +08:00
lizhenyun01
e51f018577
support chunk_prefill in fa3
2025-07-23 12:19:20 +08:00
Ryan
95b5af24db
[SOT] Add sot warmup (NVIDIA GPU Only) ( #2929 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* add sot warmup
* fix code style
* change batch_size list
* add param to config
* rm free_list settings && set sot_warmup_sizes
* finish debug with dynamic dims by type annotations
* add profile_run guard
* rm sth useless
2025-07-22 21:36:14 +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
Nyakku Shigure
48e6a0ca26
[SOT] Mark dynamic dims by type annotations ( #2771 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* [SOT] Mark dynamic dims by type annotations
* fix conflict of forward_meta
* mark more attn backend
* fix missing annotated and add env SOT_SPECIALIZED_DIM_NUMBERS
* auto infer implicit 0 dim dynamic dim
* revert manual marked dims
* revert missing update
* auto infer can use unsafe code in warmup stage
* check -> type_match
* fix codestyle
* restore blank line
* empty commit
* add need_warmup nonlocal;
* add doc for resolver
* add missing type hints
* unquote "ForwardMeta"
2025-07-22 00:23:52 -07:00
lifulll
2c6a9e887e
native top_p_sampling ( #2901 )
2025-07-22 14:09:59 +08:00
K11OntheBoat
8020927f50
[BugFix] Rename attention params of deepseekv3 ( #2939 )
...
Co-authored-by: K11OntheBoat <“ruianmaidanglao@163.com ”>
2025-07-22 14:01:30 +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
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
