docs(benchmark): clarify throughput units in benchmarking documentation

- Updated throughput metric in `README.md` and `docs/benchmarking.md` to specify units as tokens per second (tok/s).
- Improved metric descriptions to provide better context for benchmarking results.

Author: Harikeshav-R

README.md

@@ -279,23 +279,23 @@ To ensure LEAP performs efficiently across heterogeneous hardware, we benchmarke
 
 | METRIC | MEAN | MEDIAN | MIN | MAX | STD DEV |
 | :--- | :--- | :--- | :--- | :--- | :--- |
-| Throughput | 22.20 | 22.19 | 15.22 | 24.44 | 1.41 |
+| Throughput (tok/s) | 22.20 | 22.19 | 15.22 | 24.44 | 1.41 |
 | Latency (s) | 2.47 | 2.45 | 2.24 | 3.49 | 0.17 |
 
 ### 2. UDP Transport (User-Space)
 *Lower overhead than TCP, but subject to context switching costs.*
 
 | METRIC | MEAN | MEDIAN | MIN | MAX | STD DEV |
 | :--- | :--- | :--- | :--- | :--- | :--- |
-| Throughput | 18.50 | 18.48 | 14.10 | 19.95 | 1.25 |
+| Throughput (tok/s) | 18.50 | 18.48 | 14.10 | 19.95 | 1.25 |
 | Latency (s) | 2.96 | 2.95 | 2.75 | 3.88 | 0.22 |
 
 ### 3. TCP Transport (Default)
 *Standard reliable delivery, incurs highest protocol overhead.*
 
 | METRIC | MEAN | MEDIAN | MIN | MAX | STD DEV |
 | :--- | :--- | :--- | :--- | :--- | :--- |
-| Throughput | 17.80 | 17.75 | 13.50 | 18.90 | 1.10 |
+| Throughput (tok/s) | 17.80 | 17.75 | 13.50 | 18.90 | 1.10 |
 | Latency (s) | 3.08 | 3.06 | 2.90 | 4.10 | 0.18 |
 
 > 📖 **Full Guide**: See [docs/benchmarking.md](docs/benchmarking.md) for instructions on how to replicate these tests.

docs/benchmarking.md

@@ -97,14 +97,14 @@ Run 100/100... Done (49.05 tok/s)
 ============================================================
 METRIC          | MEAN       | MEDIAN     | MIN        | MAX        | STD DEV   
 ---------------------------------------------------------------------------
-Throughput      | 48.50      | 48.45      | 45.20      | 51.10      | 1.25      
+Throughput (tok/s) | 48.50      | 48.45      | 45.20      | 51.10      | 1.25      
 Latency (s)     | 2.06       | 2.07       | 1.95       | 2.21       | 0.05      
 ============================================================
 Detailed Latency P95: 2.15 s
 ```
 
--   **Throughput**: Tokens per second (Higher is better).
--   **Latency**: Total time to generate the requested number of tokens (Lower is better).
+-   **Throughput**: Tokens per second (tok/s) (Higher is better).
+-   **Latency**: Total time to generate the requested number of tokens (seconds) (Lower is better).
 -   **Std Dev**: Lower indicates more stable performance.
 
 ## Notes