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
/
tests
131 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
11 days ago
hello_acl.cpp
2.23 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
11 days ago
test_attention_decode.cpp
16.5 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
11 days ago
test_attention_layer.cpp
9.97 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
11 days ago
test_batch_correctness.cpp
4.44 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
11 days ago
test_batch_decode.cpp
3.49 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
11 days ago
test_chat_flow.sh
2.71 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
11 days ago
test_engine_smoke.cpp
283 Bytes
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
11 days ago
test_layer_forward.cpp
8.7 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
11 days ago
test_linear_hf.cpp
2.92 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
11 days ago
test_model_config.cpp
5.46 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
11 days ago
test_moe_layer.cpp
34.8 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
11 days ago
test_op_support.cpp
8.9 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
11 days ago
test_rms_norm.cpp
3.44 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
11 days ago
test_rope.cpp
4.94 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
11 days ago
test_rope_fused.cpp
6.64 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
11 days ago
test_rope_manual.cpp
3.1 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
11 days ago
test_runner.cpp
2.88 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
11 days ago
test_safetensors.cpp
4.05 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
11 days ago
test_tokenizer.cpp
2.08 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
11 days ago
test_weight_load.cpp
3.8 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU
11 days ago