ModelZoo

# Enter the spacemit-ort library path
# cd {spacemit_ort_lib}/
export LD_LIBRARY_PATH=./lib/

# Replace ${model_path} with your own model file path and ${num of cores} with the number of CPU cores to use
./bin/onnxruntime_perf_test ${model_path} -e spacemit -r 10 -x 1 -S 1 -s -c 1 -i "SPACEMIT_EP_INTRA_THREAD_NUM|${num of cores}" -I

# Example output:
using SpaceMITExecutionProvider
setting SPACEMIT_EP_INTRA_THREAD_NUM : 4
Setting intra_op_num_threads to 1
Session creation time cost: 0.169475 s
First inference time cost: 109 ms
Total inference time cost: 0.0727021 s
Total inference requests: 10
Average inference time cost total: 7.270205 ms
Total inference run time: 0.0727619 s
Number of inferences per second: 137.435
Avg CPU usage: 62 %
Peak working set size: 91336704 bytes
Avg CPU usage:62
Peak working set size:91336704
Runs:10
Min Latency: 0.00720383 s
Max Latency: 0.00730163 s
P50 Latency: 0.00727787 s
P90 Latency: 0.00730163 s
P95 Latency: 0.00730163 s
P99 Latency: 0.00730163 s
P999 Latency: 0.00730163 s

# "Average inference time cost total" indicates the single-frame inference latency.

# Enter the spacemit-llama.cpp library path
# cd {spacemit-llama.cpp}/
export LD_LIBRARY_PATH=./lib/

# Replace ${model_path} with your own model file path and ${num of cores} with the number of CPU cores to use
./bin/llama-bench -m ${model_path} -t ${num of cores} -p 128 -n 128 -mmp 0 -fa 1 -ub 128

# Example output:
CPU_RISCV64_SPACEMIT: tcm is available, blk_size: 393216, blk_num: 8, is_fake_tcm: 0
CPU_RISCV64_SPACEMIT: num_cores: 16, num_perfer_cores: 8, perfer_core_arch_id: a064, exclude_main_thread: 0, use_ime1: 0, use_ime2: 1, mem_backend: HPAGE, cpu_mask: ff00, aicpu_id_offset: 8
CPU_RISCV64_SPACEMIT: alloc_chunk: open(/dev/tcm_sync_mem) failed, errno=2
CPU_RISCV64_SPACEMIT: failed to allocate init_barrier from shared mem, falling back to heap
| model                          |       size |     params | backend    | threads | n_ubatch | fa | mmap |            test |                  t/s |
| ------------------------------ | ---------: | ---------: | ---------- | ------: | -------: | -: | ---: | --------------: | -------------------: |
| qwen3 0.6B Q4_0                | 358.78 MiB |   596.05 M | CPU        |       8 |      128 |  1 |    0 |           pp128 |        499.75 ± 0.22 |
| qwen3 0.6B Q4_0                | 358.78 MiB |   596.05 M | CPU        |       8 |      128 |  1 |    0 |           tg128 |         53.35 ± 0.03 |

export LD_LIBRARY_PATH=./spacemit-llama.cpp/lib:./spacemit_ort/lib
export SPACEMIT_EP_DENSE_ACCURACY_LEVEL=1

llama-server -m qwen3vl-30b-text-q4_1.gguf --media-backend smt --smt-config-dir ./ -ctk f16 -ctv f16 -t 8 -c 1024 --host 0.0.0.0 --port 8080 --reasoning-budget 0 --reasoning off