MoYoYoTech
/

llm_mutil_npu

Model card Files Files and versions

llm_mutil_npu / include

66.4 kB

Ctrl+K

Ctrl+K

2 contributors

History: 1 commit

xianglarry's picture

Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU

4b9fefd about 1 month ago

acl_common.h

3.9 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU about 1 month ago
acl_runtime.h

1.16 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU about 1 month ago
aclnn_ops.h

15.8 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU about 1 month ago
device_weights.h

3.51 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU about 1 month ago
engine.h

17.9 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU about 1 month ago
hccl_comm.h

3.84 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU about 1 month ago
model_config.h

2.29 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU about 1 month ago
rope.h

4.87 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU about 1 month ago
runner.h

5.84 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU about 1 month ago
safetensors_loader.h

2.63 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU about 1 month ago
tokenizer.h

1.51 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU about 1 month ago
workspace_pool.h

3.09 kB
Initial C++ aclnn EAGER inference for Qwen3-235B-A22B MoE on Ascend 910 × 16 NPU about 1 month ago