GithubStar/ncnn
1
0
Fork 0
mirror of https://github.com/Tencent/ncnn.git synced 2026-10-22 16:55:13 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
master
ncnn/benchmark/models/llm
T
History
nihui 60bfa40044 sdpa flash attention x86 optimization, llm models enable gqa, dispatch for avx2 bfloat2float (#6923) 
* enable gqa
* update perf test
2026-09-01 17:35:42 +08:00
..
hunyuan_0.5b_instruct_decoder.ncnn.param
sdpa flash attention x86 optimization, llm models enable gqa, dispatch for avx2 bfloat2float (#6923)
2026-09-01 17:35:42 +08:00
hunyuan_0.5b_instruct_proj_out.ncnn.param
benchncnn_llm (#6711)
2026-05-13 11:38:29 +08:00
llama3.2_1b_decoder.ncnn.param
sdpa flash attention x86 optimization, llm models enable gqa, dispatch for avx2 bfloat2float (#6923)
2026-09-01 17:35:42 +08:00
llama3.2_1b_proj_out.ncnn.param
benchncnn_llm (#6711)
2026-05-13 11:38:29 +08:00
minicpm4_0.5b_decoder.ncnn.param
sdpa flash attention x86 optimization, llm models enable gqa, dispatch for avx2 bfloat2float (#6923)
2026-09-01 17:35:42 +08:00
minicpm4_0.5b_proj_out.ncnn.param
benchncnn_llm (#6711)
2026-05-13 11:38:29 +08:00
qwen2.5_0.5b_decoder.ncnn.param
sdpa flash attention x86 optimization, llm models enable gqa, dispatch for avx2 bfloat2float (#6923)
2026-09-01 17:35:42 +08:00
qwen2.5_0.5b_proj_out.ncnn.param
benchncnn_llm (#6711)
2026-05-13 11:38:29 +08:00
qwen3_0.6b_decoder.ncnn.param
sdpa flash attention x86 optimization, llm models enable gqa, dispatch for avx2 bfloat2float (#6923)
2026-09-01 17:35:42 +08:00
qwen3_0.6b_proj_out.ncnn.param
benchncnn_llm (#6711)
2026-05-13 11:38:29 +08:00
tinyllama_1.1b_decoder.ncnn.param
sdpa flash attention x86 optimization, llm models enable gqa, dispatch for avx2 bfloat2float (#6923)
2026-09-01 17:35:42 +08:00
tinyllama_1.1b_proj_out.ncnn.param
benchncnn_llm (#6711)
2026-05-13 11:38:29 +08:00
youtu_llm_2b_decoder.ncnn.param
benchncnn_llm (#6711)
2026-05-13 11:38:29 +08:00
youtu_llm_2b_proj_out.ncnn.param
benchncnn_llm (#6711)
2026-05-13 11:38:29 +08:00