# HELP gufo_device_lost_total Confirmed GPU context losses
# TYPE gufo_device_lost_total counter
gufo_device_lost_total 0
# HELP llamacpp:prompt_tokens_total Total prompt tokens processed, excluding cache hits
# TYPE llamacpp:prompt_tokens_total counter
llamacpp:prompt_tokens_total 213784
# HELP llamacpp:prompt_tokens_cached_total Total prompt tokens reused from cache
# TYPE llamacpp:prompt_tokens_cached_total counter
llamacpp:prompt_tokens_cached_total 38070188
# HELP llamacpp:prompt_seconds_total Prompt process time
# TYPE llamacpp:prompt_seconds_total counter
llamacpp:prompt_seconds_total 215.41327585600013
# HELP llamacpp:tokens_predicted_total Total tokens generated
# TYPE llamacpp:tokens_predicted_total counter
llamacpp:tokens_predicted_total 268387
# HELP llamacpp:tokens_predicted_seconds_total Predict process time
# TYPE llamacpp:tokens_predicted_seconds_total counter
llamacpp:tokens_predicted_seconds_total 6520.4400505340027
# HELP llamacpp:n_tokens_max Largest observed n_tokens.
# TYPE llamacpp:n_tokens_max counter
llamacpp:n_tokens_max 222926
# HELP llamacpp:spec_decode_num_drafts_total Total speculative verification rounds
# TYPE llamacpp:spec_decode_num_drafts_total counter
llamacpp:spec_decode_num_drafts_total 83278
# HELP llamacpp:spec_decode_num_draft_tokens_total Total draft tokens proposed
# TYPE llamacpp:spec_decode_num_draft_tokens_total counter
llamacpp:spec_decode_num_draft_tokens_total 234468
# HELP llamacpp:spec_decode_num_accepted_tokens_total Total draft tokens accepted
# TYPE llamacpp:spec_decode_num_accepted_tokens_total counter
llamacpp:spec_decode_num_accepted_tokens_total 180837
# HELP gufo_spec_lookup_tokens_total Total prompt-lookup copies proposed
# TYPE gufo_spec_lookup_tokens_total counter
gufo_spec_lookup_tokens_total 17416
# HELP gufo_spec_lookup_accepted_tokens_total Total prompt-lookup copies accepted
# TYPE gufo_spec_lookup_accepted_tokens_total counter
gufo_spec_lookup_accepted_tokens_total 13985
# HELP llamacpp:prompt_tokens_seconds Prompt processing speed in tokens per second
# TYPE llamacpp:prompt_tokens_seconds gauge
llamacpp:prompt_tokens_seconds 594.36656560014194
# HELP llamacpp:predicted_tokens_seconds Generation speed in tokens per second
# TYPE llamacpp:predicted_tokens_seconds gauge
llamacpp:predicted_tokens_seconds 53.07443936596944
# HELP llamacpp:requests_processing Number of admitted requests, including cache preparation
# TYPE llamacpp:requests_processing gauge
llamacpp:requests_processing 0
# HELP llamacpp:requests_deferred Number of requests waiting for a session
# TYPE llamacpp:requests_deferred gauge
llamacpp:requests_deferred 0
# HELP llamacpp:kv_cache_usage_ratio In-flight prompt and generated tokens over sessions times context; excludes retained cache
# TYPE llamacpp:kv_cache_usage_ratio gauge
llamacpp:kv_cache_usage_ratio 0
