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
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
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
xiaoxiaohehe001
ad319a87cc
support fa3 rope3d ( #3622 )
2025-08-27 11:31:29 +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
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
lizhenyun01
e51f018577
support chunk_prefill in fa3
2025-07-23 12:19:20 +08:00
lifulll
2c6a9e887e
native top_p_sampling ( #2901 )
2025-07-22 14:09:59 +08:00
Zero Rains
25698d56d1
polish code with new pre-commit rule ( #2923 )
2025-07-19 23:19:27 +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
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
Ryan
b0f525955c
[SOT] Remove breakgraph in post processing && fix datatype ( #2780 )
2025-07-10 11:26:00 +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
Yuanle Liu
240bdac2a4
[feat] support fa3 backend for pd disaggregated ( #2695 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* support fa3 backend run in pd disaggregated
* support fa3 backend run in pd disaggregated
* support fa3 backend run in pd disaggregated
* support fa3 backend run in pd disaggregated
* delete use_fast_ffn
2025-07-03 22:33:27 +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
