server : fix divide-by-zero in metrics reporting

[aviallon]

Before any generation is made by llama.cpp server, the /metrics endpoint reported a -nan value resulting from a divide by zero. This PR ensures that the division by zero never occurs.

Before (notice n_busy_slots_per_decode):

# HELP llamacpp:prompt_tokens_total Number of prompt tokens processed.
# TYPE llamacpp:prompt_tokens_total counter
llamacpp:prompt_tokens_total 0
# HELP llamacpp:prompt_seconds_total Prompt process time
# TYPE llamacpp:prompt_seconds_total counter
llamacpp:prompt_seconds_total 0
# HELP llamacpp:tokens_predicted_total Number of generation tokens processed.
# TYPE llamacpp:tokens_predicted_total counter
llamacpp:tokens_predicted_total 0
# HELP llamacpp:tokens_predicted_seconds_total Predict process time
# TYPE llamacpp:tokens_predicted_seconds_total counter
llamacpp:tokens_predicted_seconds_total 0
# HELP llamacpp:n_decode_total Total number of llama_decode() calls
# TYPE llamacpp:n_decode_total counter
llamacpp:n_decode_total 0
# HELP llamacpp:n_busy_slots_per_decode Average number of busy slots per llama_decode() call
# TYPE llamacpp:n_busy_slots_per_decode counter
llamacpp:n_busy_slots_per_decode -nan
# HELP llamacpp:prompt_tokens_seconds Average prompt throughput in tokens/s.
# TYPE llamacpp:prompt_tokens_seconds gauge
llamacpp:prompt_tokens_seconds 0
# HELP llamacpp:predicted_tokens_seconds Average generation throughput in tokens/s.
# TYPE llamacpp:predicted_tokens_seconds gauge
llamacpp:predicted_tokens_seconds 0
# HELP llamacpp:kv_cache_usage_ratio KV-cache usage. 1 means 100 percent usage.
# TYPE llamacpp:kv_cache_usage_ratio gauge
llamacpp:kv_cache_usage_ratio 0
# HELP llamacpp:kv_cache_tokens KV-cache tokens.
# TYPE llamacpp:kv_cache_tokens gauge
llamacpp:kv_cache_tokens 0
# HELP llamacpp:requests_processing Number of requests processing.
# TYPE llamacpp:requests_processing gauge
llamacpp:requests_processing 0
# HELP llamacpp:requests_deferred Number of requests deferred.
# TYPE llamacpp:requests_deferred gauge
llamacpp:requests_deferred 0

After:

# HELP llamacpp:prompt_tokens_total Number of prompt tokens processed.
# TYPE llamacpp:prompt_tokens_total counter
llamacpp:prompt_tokens_total 0
# HELP llamacpp:prompt_seconds_total Prompt process time
# TYPE llamacpp:prompt_seconds_total counter
llamacpp:prompt_seconds_total 0
# HELP llamacpp:tokens_predicted_total Number of generation tokens processed.
# TYPE llamacpp:tokens_predicted_total counter
llamacpp:tokens_predicted_total 0
# HELP llamacpp:tokens_predicted_seconds_total Predict process time
# TYPE llamacpp:tokens_predicted_seconds_total counter
llamacpp:tokens_predicted_seconds_total 0
# HELP llamacpp:n_decode_total Total number of llama_decode() calls
# TYPE llamacpp:n_decode_total counter
llamacpp:n_decode_total 0
# HELP llamacpp:n_busy_slots_per_decode Average number of busy slots per llama_decode() call
# TYPE llamacpp:n_busy_slots_per_decode counter
llamacpp:n_busy_slots_per_decode 0
# HELP llamacpp:prompt_tokens_seconds Average prompt throughput in tokens/s.
# TYPE llamacpp:prompt_tokens_seconds gauge
llamacpp:prompt_tokens_seconds 0
# HELP llamacpp:predicted_tokens_seconds Average generation throughput in tokens/s.
# TYPE llamacpp:predicted_tokens_seconds gauge
llamacpp:predicted_tokens_seconds 0
# HELP llamacpp:kv_cache_usage_ratio KV-cache usage. 1 means 100 percent usage.
# TYPE llamacpp:kv_cache_usage_ratio gauge
llamacpp:kv_cache_usage_ratio 0
# HELP llamacpp:kv_cache_tokens KV-cache tokens.
# TYPE llamacpp:kv_cache_tokens gauge
llamacpp:kv_cache_tokens 0
# HELP llamacpp:requests_processing Number of requests processing.
# TYPE llamacpp:requests_processing gauge
llamacpp:requests_processing 0
# HELP llamacpp:requests_deferred Number of requests deferred.
# TYPE llamacpp:requests_deferred gauge
llamacpp:requests_deferred 0