diff --git a/docs/llamacpp_ops.md b/docs/llamacpp_ops.md
index 0cce6279d..49dac2b7a 100644
--- a/docs/llamacpp_ops.md
+++ b/docs/llamacpp_ops.md
@@ -51,6 +51,7 @@
 | SOFTCAP | ✅ |
 | SQR | ✅ |
 | SQRT | ✅ |
+| SSM_CONV | ✅ |
 | STEP | ✅ |
 | SUB | ✅ |
 | SUM_ROWS | ✅ |
@@ -70,7 +71,6 @@
 | MUL_MAT | 🟡 |
 | MUL_MAT_ID | 🟡 |
 | OPT_STEP_ADAMW | 🟡 |
-| OUT_PROD | 🟡 |
 | PAD | 🟡 |
 | POOL_2D | 🟡 |
 | REPEAT_BACK | 🟡 |
@@ -85,10 +85,10 @@
 | SILU_BACK | 🟡 |
 | SOFT_MAX | 🟡 |
 | SOFT_MAX_BACK | 🟡 |
-| SSM_CONV | 🟡 |
 | SSM_SCAN | 🟡 |
 | SUM | 🟡 |
 | UPSCALE | 🟡 |
+| OUT_PROD | ❌ |
 
 Tips: ✅ supported, 🟡 partially supported, ❌ fail, ❓ unsupported, 🔍 unknown
 
@@ -96,125 +96,72 @@ Tips: ✅ supported, 🟡 partially supported, ❌ fail, ❓ unsupported, 🔍 u
 
 | Operator | Previous | Current |
 | --- | --- | --- |
-| CONV_TRANSPOSE_1D | partial (🟡) | supported (✅) |
+| OUT_PROD | partial (🟡) | fail (❌) |
+| SSM_CONV | partial (🟡) | supported (✅) |
 
-#### CONV_TRANSPOSE_1D log (partial -> supported)
+#### OUT_PROD log (partial -> fail)
 ```text
-  CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[1,1,1,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[1,1,1,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[1,1,1,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[1,1,1,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[1,1,1,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[1,1,1,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[1,1,1,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[3,1,1,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[3,1,1,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[3,1,1,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[3,1,1,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[3,1,1,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[3,1,1,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[3,1,1,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[3,1,1,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[3,1,1,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[1337,1,1,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[1337,1,1,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[1337,1,1,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[1337,1,1,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[1337,1,1,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[1337,1,1,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[1337,1,1,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[1337,1,1,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[1337,1,1,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[1,1,7,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[1,1,7,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[1,1,7,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[1,1,7,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[1,1,7,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[1,1,7,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[1,1,7,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[1,1,7,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[1,1,7,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[3,1,7,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[3,1,7,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[3,1,7,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[3,1,7,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[3,1,7,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[3,1,7,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[3,1,7,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[3,1,7,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[3,1,7,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[1337,1,7,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[1337,1,7,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[1337,1,7,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[1337,1,7,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[1337,1,7,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[1337,1,7,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[1337,1,7,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[1337,1,7,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[1337,1,7,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[1,9,1,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[1,9,1,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[1,9,1,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[1,9,1,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[1,9,1,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[1,9,1,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[1,9,1,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[1,9,1,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[1,9,1,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[3,9,1,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[3,9,1,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[3,9,1,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[3,9,1,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[3,9,1,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[3,9,1,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[3,9,1,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[3,9,1,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[3,9,1,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[1337,9,1,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[1337,9,1,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,1,1,1],ne_kernel=[1337,9,1,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[1337,9,1,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[1337,9,1,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[1337,9,1,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[1337,9,1,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[1337,9,1,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,1,1,1],ne_kernel=[1337,9,1,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[1,9,7,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[1,9,7,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[1,9,7,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[1,9,7,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[1,9,7,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[1,9,7,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[1,9,7,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[1,9,7,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[1,9,7,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[3,9,7,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[3,9,7,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[3,9,7,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[3,9,7,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[3,9,7,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[3,9,7,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[3,9,7,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[3,9,7,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[3,9,7,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[1337,9,7,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[1337,9,7,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[1,7,1,1],ne_kernel=[1337,9,7,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[1337,9,7,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[1337,9,7,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,7,1,1],ne_kernel=[1337,9,7,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[1337,9,7,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[1337,9,7,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[13,7,1,1],ne_kernel=[1337,9,7,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[197,32,1,1],ne_kernel=[16,32,32,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[3,2,1,1],ne_kernel=[2,3,2,1],s0=3,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[3,2,1,1],ne_kernel=[2,3,2,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[3,2,1,1],ne_kernel=[2,3,2,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[3,2,1,1],ne_kernel=[3,2,2,1],s0=2,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[3,2,1,1],ne_kernel=[3,2,2,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[3,2,1,1],ne_kernel=[3,1,2,1],s0=1,p0=0,d0=1): OK
-  CONV_TRANSPOSE_1D(ne_input=[2,1,1,1],ne_kernel=[3,1,1,1],s0=1,p0=0,d0=1): OK
-  116/116 tests passed
+new_pool_for_device: device 0 use vmm pool
+Testing 2 devices
+
+Backend 1/2: CANN0
+  Device description: Ascend910B1
+  Device memory: 62420 MB (62055 MB free)
+
+/__w/Ascend-CI/Ascend-CI/llama.cpp/ggml/src/ggml-cann/aclnn_ops.cpp:3723: GGML_ASSERT(dst->ne[0] == nr) failed
+libggml-base.so.0(+0x151a4)[0xffff9e6951a4]
+libggml-base.so.0(ggml_print_backtrace+0x21c)[0xffff9e69565c]
+libggml-base.so.0(ggml_abort+0x134)[0xffff9e695824]
+libggml-cann.so.0(_Z18ggml_cann_ssm_convR25ggml_backend_cann_contextP11ggml_tensor+0x414)[0xffff9e051a84]
+libggml-cann.so.0(+0x26820)[0xffff9e056820]
+libggml-cann.so.0(+0x27358)[0xffff9e057358]
+libggml-base.so.0(ggml_backend_graph_compute+0x14)[0xffff9e6ab184]
+libggml-base.so.0(ggml_backend_compare_graph_backend+0x170)[0xffff9e6afc70]
+./test-backend-ops(+0x80f7c)[0xaaaac70c0f7c]
+./test-backend-ops(+0x36618)[0xaaaac7076618]
+./test-backend-ops(+0x16a10)[0xaaaac7056a10]
+/lib/aarch64-linux-gnu/libc.so.6(+0x273fc)[0xffff9e1f73fc]
+/lib/aarch64-linux-gnu/libc.so.6(__libc_start_main+0x98)[0xffff9e1f74cc]
+./test-backend-ops(+0x180f0)[0xaaaac70580f0]
+```
+
+#### SSM_CONV log (partial -> supported)
+```text
+new_pool_for_device: device 0 use vmm pool
+Testing 2 devices
+
+Backend 1/2: CANN0
+  Device description: Ascend910B1
+  Device memory: 62420 MB (62051 MB free)
+
+  SSM_CONV(type=f32,ne_a=[3,1024,1,1],ne_b=[3,1024,1,1]): OK
+  SSM_CONV(type=f32,ne_a=[6,1024,1,1],ne_b=[3,1024,1,1]): OK
+  SSM_CONV(type=f32,ne_a=[3,1024,4,1],ne_b=[3,1024,1,1]): OK
+  SSM_CONV(type=f32,ne_a=[3,1536,1,1],ne_b=[3,1536,1,1]): OK
+  SSM_CONV(type=f32,ne_a=[6,1536,1,1],ne_b=[3,1536,1,1]): OK
+  SSM_CONV(type=f32,ne_a=[3,1536,4,1],ne_b=[3,1536,1,1]): OK
+  SSM_CONV(type=f32,ne_a=[3,2048,1,1],ne_b=[3,2048,1,1]): OK
+  SSM_CONV(type=f32,ne_a=[6,2048,1,1],ne_b=[3,2048,1,1]): OK
+  SSM_CONV(type=f32,ne_a=[3,2048,4,1],ne_b=[3,2048,1,1]): OK
+  SSM_CONV(type=f32,ne_a=[4,1024,1,1],ne_b=[4,1024,1,1]): OK
+  SSM_CONV(type=f32,ne_a=[8,1024,1,1],ne_b=[4,1024,1,1]): OK
+  SSM_CONV(type=f32,ne_a=[4,1024,4,1],ne_b=[4,1024,1,1]): OK
+  SSM_CONV(type=f32,ne_a=[4,1536,1,1],ne_b=[4,1536,1,1]): OK
+  SSM_CONV(type=f32,ne_a=[8,1536,1,1],ne_b=[4,1536,1,1]): OK
+  SSM_CONV(type=f32,ne_a=[4,1536,4,1],ne_b=[4,1536,1,1]): OK
+  SSM_CONV(type=f32,ne_a=[4,2048,1,1],ne_b=[4,2048,1,1]): OK
+  SSM_CONV(type=f32,ne_a=[8,2048,1,1],ne_b=[4,2048,1,1]): OK
+  SSM_CONV(type=f32,ne_a=[4,2048,4,1],ne_b=[4,2048,1,1]): OK
+  SSM_CONV(type=f32,ne_a=[9,1024,1,1],ne_b=[9,1024,1,1]): OK
+  SSM_CONV(type=f32,ne_a=[18,1024,1,1],ne_b=[9,1024,1,1]): OK
+  SSM_CONV(type=f32,ne_a=[9,1024,4,1],ne_b=[9,1024,1,1]): OK
+  SSM_CONV(type=f32,ne_a=[9,1536,1,1],ne_b=[9,1536,1,1]): OK
+  SSM_CONV(type=f32,ne_a=[18,1536,1,1],ne_b=[9,1536,1,1]): OK
+  SSM_CONV(type=f32,ne_a=[9,1536,4,1],ne_b=[9,1536,1,1]): OK
+  SSM_CONV(type=f32,ne_a=[9,2048,1,1],ne_b=[9,2048,1,1]): OK
+  SSM_CONV(type=f32,ne_a=[18,2048,1,1],ne_b=[9,2048,1,1]): OK
+  SSM_CONV(type=f32,ne_a=[9,2048,4,1],ne_b=[9,2048,1,1]): OK
+  27/27 tests passed
   Backend CANN0: OK
 Backend 2/2: CPU
   Skipping CPU backend