26 lines
2.1 KiB
Plaintext
26 lines
2.1 KiB
Plaintext
# HELP vllm:spec_decode_num_drafts_total Number of spec decoding drafts.
|
|
# TYPE vllm:spec_decode_num_drafts_total counter
|
|
vllm:spec_decode_num_drafts_total{engine="0",model_name="qwen3.8-flash-next"} 42344.0
|
|
# HELP vllm:spec_decode_num_drafts_created Number of spec decoding drafts.
|
|
# TYPE vllm:spec_decode_num_drafts_created gauge
|
|
vllm:spec_decode_num_drafts_created{engine="0",model_name="qwen3.8-flash-next"} 1.7897410011528008e+09
|
|
# HELP vllm:spec_decode_num_draft_tokens_total Number of draft tokens.
|
|
# TYPE vllm:spec_decode_num_draft_tokens_total counter
|
|
vllm:spec_decode_num_draft_tokens_total{engine="0",model_name="qwen3.8-flash-next"} 84688.0
|
|
# HELP vllm:spec_decode_num_draft_tokens_created Number of draft tokens.
|
|
# TYPE vllm:spec_decode_num_draft_tokens_created gauge
|
|
vllm:spec_decode_num_draft_tokens_created{engine="0",model_name="qwen3.8-flash-next"} 1.7897410011528184e+09
|
|
# HELP vllm:spec_decode_num_accepted_tokens_total Number of accepted tokens.
|
|
# TYPE vllm:spec_decode_num_accepted_tokens_total counter
|
|
vllm:spec_decode_num_accepted_tokens_total{engine="0",model_name="qwen3.8-flash-next"} 56280.0
|
|
# HELP vllm:spec_decode_num_accepted_tokens_created Number of accepted tokens.
|
|
# TYPE vllm:spec_decode_num_accepted_tokens_created gauge
|
|
vllm:spec_decode_num_accepted_tokens_created{engine="0",model_name="qwen3.8-flash-next"} 1.7897410011528296e+09
|
|
# HELP vllm:spec_decode_num_accepted_tokens_per_pos_total Accepted tokens per draft position.
|
|
# TYPE vllm:spec_decode_num_accepted_tokens_per_pos_total counter
|
|
vllm:spec_decode_num_accepted_tokens_per_pos_total{engine="0",model_name="qwen3.8-flash-next",position="0"} 32436.0
|
|
vllm:spec_decode_num_accepted_tokens_per_pos_total{engine="0",model_name="qwen3.8-flash-next",position="1"} 23844.0
|
|
# HELP vllm:spec_decode_num_accepted_tokens_per_pos_created Accepted tokens per draft position.
|
|
# TYPE vllm:spec_decode_num_accepted_tokens_per_pos_created gauge
|
|
vllm:spec_decode_num_accepted_tokens_per_pos_created{engine="0",model_name="qwen3.8-flash-next",position="0"} 1.7897410011528459e+09
|
|
vllm:spec_decode_num_accepted_tokens_per_pos_created{engine="0",model_name="qwen3.8-flash-next",position="1"} 1.78974100115285e+09 |