ci: bench: remove total pp and tg as it is not accurate

This commit is contained in:
Pierrick HYMBERT 2024-04-05 00:17:48 +02:00
parent 1534d903d7
commit 3694026669

View file

@ -235,8 +235,8 @@ jobs:
- Concurrent users: ${{ env.N_USERS }}, duration: ${{ github.event.inputs.duration || env.DURATION }}
- HTTP request : avg=${{ env.HTTP_REQ_DURATION_AVG }}ms p(90)=${{ env.HTTP_REQ_DURATION_P_90_ }}ms fails=${{ env.HTTP_REQ_FAILED_PASSES }}, finish reason: stop=${{ env.LLAMACPP_COMPLETIONS_STOP_RATE_PASSES }} truncated=${{ env.LLAMACPP_COMPLETIONS_TRUNCATED_RATE_PASSES }}
- Prompt processing (pp): avg=${{ env.LLAMACPP_PROMPT_PROCESSING_SECOND_AVG }}tk/s p(90)=${{ env.LLAMACPP_PROMPT_PROCESSING_SECOND_P_90_ }}tk/s **total=${{ env.LLAMACPP_PROMPT_TOKENS_TOTAL_COUNTER_RATE }}tk/s**
- Token generation (tg): avg=${{ env.LLAMACPP_TOKENS_SECOND_AVG }}tk/s p(90)=${{ env.LLAMACPP_TOKENS_SECOND_P_90_ }}tk/s **total=${{ env.LLAMACPP_COMPLETION_TOKENS_TOTAL_COUNTER_RATE }}tk/s**
- Prompt processing (pp): avg=${{ env.LLAMACPP_PROMPT_PROCESSING_SECOND_AVG }}tk/s p(90)=${{ env.LLAMACPP_PROMPT_PROCESSING_SECOND_P_90_ }}tk/s
- Token generation (tg): avg=${{ env.LLAMACPP_TOKENS_SECOND_AVG }}tk/s p(90)=${{ env.LLAMACPP_TOKENS_SECOND_P_90_ }}tk/s
- ${{ env.BENCH_GRAPH_XLABEL }}