lzy
af49b81ffd
supports dynamic Cfp8 ( #3767 )
...
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Deploy GitHub Pages / deploy (push) Has been cancelled
* supports dynamic Cfp8
* add unittest
2025-09-07 20:41:29 -07:00
周周周
f6f726c773
clean code in sttantion ( #3917 )
2025-09-05 20:49:01 +08:00
xiaoxiaohehe001
f265a26f8b
support mtp rope_3d ( #3791 )
...
* support mtp rope_3d
* Update speculate_write_cache_with_rope_kernel.cu
2025-09-04 17:18:05 +08:00
Yuan Xiaolan
fa58a9fa8f
qk norm for speculate decode C16 ( #3637 )
2025-09-03 14:53:56 +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
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
Ryan
ed6bff215a
fix custom op order rms_norm_eps ( #3348 )
2025-08-13 10:12:49 +08:00
Yuan Xiaolan
7ce00e597c
support qk norm ( #3145 )
2025-08-05 16:46:14 +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 )
...
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
jiangjiajun
684703fd72
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
