# HELP llamacpp:prompt_tokens_total Number of prompt tokens processed, excluding cached tokens
# TYPE llamacpp:prompt_tokens_total counter
llamacpp:prompt_tokens_total 34
# HELP llamacpp:prompt_tokens_cached_total Number of prompt tokens reused from the cache
# TYPE llamacpp:prompt_tokens_cached_total counter
llamacpp:prompt_tokens_cached_total 0
# HELP llamacpp:prompt_seconds_total Total time spent processing prompts
# TYPE llamacpp:prompt_seconds_total counter
llamacpp:prompt_seconds_total 0.002611
# HELP llamacpp:tokens_predicted_total Number of generation tokens processed
# TYPE llamacpp:tokens_predicted_total counter
llamacpp:tokens_predicted_total 64
# HELP llamacpp:tokens_predicted_seconds_total Total time spent generating tokens
# TYPE llamacpp:tokens_predicted_seconds_total counter
llamacpp:tokens_predicted_seconds_total 0.00991
# HELP llamacpp:n_decode_total Total number of llama_decode() calls, excluding speculative decoding and multimodal decoding
# TYPE llamacpp:n_decode_total counter
llamacpp:n_decode_total 41
# HELP llamacpp:n_tokens_max Largest observed sequence length (prompt + generation)
# TYPE llamacpp:n_tokens_max counter
llamacpp:n_tokens_max 97
# HELP llamacpp:spec_decode_num_draft_tokens_total Speculative: Total draft tokens generated
# TYPE llamacpp:spec_decode_num_draft_tokens_total counter
llamacpp:spec_decode_num_draft_tokens_total 58
# HELP llamacpp:spec_decode_num_accepted_tokens_total Speculative: Total draft tokens accepted by the target model
# TYPE llamacpp:spec_decode_num_accepted_tokens_total counter
llamacpp:spec_decode_num_accepted_tokens_total 23
# HELP llamacpp:spec_decode_num_drafts_total Speculative: Total speculative decoding verification steps
# TYPE llamacpp:spec_decode_num_drafts_total counter
llamacpp:spec_decode_num_drafts_total 20
# HELP llamacpp:prompt_tokens_seconds Average prompt throughput in tokens/s
# TYPE llamacpp:prompt_tokens_seconds gauge
llamacpp:prompt_tokens_seconds 13021.8
# HELP llamacpp:predicted_tokens_seconds Average generation throughput in tokens/s
# TYPE llamacpp:predicted_tokens_seconds gauge
llamacpp:predicted_tokens_seconds 6357.21
# 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
# HELP llamacpp:n_busy_slots_per_decode Average number of busy slots per llama_decode() call
# TYPE llamacpp:n_busy_slots_per_decode gauge
llamacpp:n_busy_slots_per_decode 1
# HELP llamacpp:spec_decode_num_accepted_tokens_per_pos_total Accepted tokens per draft position
# TYPE llamacpp:spec_decode_num_accepted_tokens_per_pos_total counter
llamacpp:spec_decode_num_accepted_tokens_per_pos_total{position="0"} 11
llamacpp:spec_decode_num_accepted_tokens_per_pos_total{position="1"} 6
llamacpp:spec_decode_num_accepted_tokens_per_pos_total{position="2"} 6
