Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
MoYoYoTech
/
llm_mutil_npu
like
0
Follow
MoYoYoTech
27
Model card
Files
Files and versions
xet
Community
main
llm_mutil_npu
/
scripts
41.5 kB
Ctrl+K
Ctrl+K
2 contributors
History:
1 commit
xianglarry
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
4b9fefd
9 days ago
bench_hccl.sh
1.79 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
9 days ago
bench_hccl_adv.sh
2.23 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
9 days ago
bench_hccl_adv2.sh
2.24 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
9 days ago
bench_pld.sh
2.43 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
9 days ago
bench_pld_k.sh
1.69 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
9 days ago
bench_pld_safe.sh
6.26 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
9 days ago
bench_tg.sh
1.35 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
9 days ago
export_vocab.py
2.85 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
9 days ago
gen_attention_reference.py
6.3 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
9 days ago
gen_gmm_reference.py
3.47 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
9 days ago
gen_mm_reference.py
903 Bytes
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
9 days ago
gen_moe_reference.py
4.39 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
9 days ago
gen_rms_norm_reference.py
1.11 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
9 days ago
regen_rope_reference.py
2.31 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
9 days ago
tp_launch.sh
2.2 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
9 days ago