docs: s390x indent blocks

Signed-off-by: Aaron Teo <[email protected]>

Author: taronaeo

docs/build-s390x.md

@@ -111,31 +111,31 @@ All models need to be converted to Big-Endian. You can achieve this in three cas
 
 ## IBM zDNN Accelerator
 
-*No direction at the moment.*
+*Only available in IBM z16 and onwards. No direction at the moment.*
 
 ## IBM Spyre Accelerator
 
 *No direction at the moment.*
 
-## Performance Optimization
-
-### Virtualization Setup
-
-We strongly recommend using only LPAR (Type-1) virtualization to get the most performance.
+## Performance Tuning
 
-Note: Type-2 virtualization is not supported at the moment, while you can get it running, the performance will not be the best.
+### 1. Virtualization Setup
 
-### IFL (Core) Count
+    We strongly recommend using only LPAR (Type-1) virtualization to get the most performance.
+    
+    Note: Type-2 virtualization is not supported at the moment, while you can get it running, the performance will not be the best.
 
-We recommend a minimum of 8 shared IFLs assigned to the LPAR. Increasing the IFL count past 8 shared IFLs will only improve Prompt Processing performance but not Token Generation.
+### 2. IFL (Core) Count
 
-Note: IFL count does not equate to vCPU count.
+    We recommend a minimum of 8 shared IFLs assigned to the LPAR. Increasing the IFL count past 8 shared IFLs will only improve Prompt Processing performance but not Token Generation.
+    
+    Note: IFL count does not equate to vCPU count.
 
-### SMT vs NOSMT (Simultaneous Multithreading)
+### 3. SMT vs NOSMT (Simultaneous Multithreading)
 
-We strongly recommend disabling SMT via the kernel boot parameters as it negatively affects performance. Please refer to your Linux distribution's guide on disabling SMT via kernel boot parameters.
+    We strongly recommend disabling SMT via the kernel boot parameters as it negatively affects performance. Please refer to your Linux distribution's guide on disabling SMT via kernel boot parameters.
 
-### BLAS vs NOBLAS
+### 4. BLAS vs NOBLAS
 
-We strongly recommend using BLAS for llama.cpp as there are no custom kernels for s390x for llama.cpp at the moment.
+    We strongly recommend using BLAS for llama.cpp as there are no custom kernels for s390x for llama.cpp at the moment.