metric: tgi_request_total increments by 2 upon every request

[thenu97]

System Info

2024-05-15T16:10:20.104786Z  INFO text_generation_launcher: Runtime environment:
Target: x86_64-unknown-linux-gnu
Cargo version: 1.75.0
Commit sha: bf700e7eef4771f280c19dbc7270c8c7c20efbbc
Docker label: N/A
nvidia-smi:
Wed May 15 16:10:19 2024       
   +---------------------------------------------------------------------------------------+
   | NVIDIA-SMI 545.23.08              Driver Version: 545.23.08    CUDA Version: 12.3     |
   |-----------------------------------------+----------------------+----------------------+
   | GPU  Name                 Persistence-M | Bus-Id        Disp.A | Volatile Uncorr. ECC |
   | Fan  Temp   Perf          Pwr:Usage/Cap |         Memory-Usage | GPU-Util  Compute M. |
   |                                         |                      |               MIG M. |
   |=========================================+======================+======================|
   |   0  NVIDIA A10G                    On  | 00000000:00:1E.0 Off |                    0 |
   |  0%   34C    P0              60W / 300W |  19020MiB / 23028MiB |      0%      Default |
   |                                         |                      |                  N/A |
   +-----------------------------------------+----------------------+----------------------+
                                                                                            
   +---------------------------------------------------------------------------------------+
   | Processes:                                                                            |
   |  GPU   GI   CI        PID   Type   Process name                            GPU Memory |
   |        ID   ID                                                             Usage      |
   |=======================================================================================|
   |    0   N/A  N/A      4235      C   ...untu/miniconda3/envs/tgi/bin/python    19008MiB |
   +---------------------------------------------------------------------------------------+

### Information

- [ ] Docker
- [ ] The CLI directly

### Tasks

- [X] An officially supported command
- [ ] My own modifications

### Reproduction

1. send a request to `chat_completions()`
2. increments request_total_count by 2

### Expected behavior

`chat_completions()` itself should increment the counter by 1. its subsequent func calls (within chat_completions()) shouldn't increment the counter
`chat_completions()` calls functions `generate` or `generate_stream_internal` depending on if steam is enabled and both these functions further increments the counter, hence incrementing the counter by 2 for every request