Summary
| Suite | Test | Latest | 1 week ago | Difference (%) | 4 weeks ago | Difference (%) |
|---|
(Suggest) initialization-latency
(Suggest) model-run-latency
(Suggest) residual-memory-usage
(Smart Tab Grouping) Topic-cold-start-initialization-latency
(Smart Tab Grouping) Topic-initialization-latency
(Smart Tab Grouping) Topic-model-run-latency
(Smart Tab Grouping) Topic-residual-memory-usage
(Smart Tab Grouping) Topic-peak-memory-usage
(Smart Tab Grouping) Embedding-cold-start-initialization-latency
(Smart Tab Grouping) Embedding-initialization-latency
(Smart Tab Grouping) Embedding-model-run-latency
(Smart Tab Grouping) Embedding-residual-memory-usage
(Smart Tab Grouping) Embedding-peak-memory-usage
(Summarizer) DISTILBART-CNN-12-6_BIG-initialization-latency
(Summarizer) QWEN2.5-0.5B-INSTRUCT_BIG-initialization-latency
(Summarizer) DISTILBART-CNN-12-6_BIG-model-run-latency
(Summarizer) QWEN2.5-0.5B-INSTRUCT_BIG-model-run-latency
(Summarizer) DISTILBART-CNN-12-6_BIG-residual-memory-usage
(Summarizer) QWEN2.5-0.5B-INSTRUCT_BIG-residual-memory-usage
(Summarizer) DISTILBART-CNN-12-6_BIG-1st-token-latency
(Summarizer) QWEN2.5-0.5B-INSTRUCT_BIG-1st-token-latency
(Summarizer) DISTILBART-CNN-12-6_BIG-decoding-latency
(Summarizer) QWEN2.5-0.5B-INSTRUCT_BIG-decoding-latency
(Summarizer) DISTILBART-CNN-12-6_BIG-decoding-tokenSpeed
(Summarizer) QWEN2.5-0.5B-INSTRUCT_BIG-decoding-tokenSpeed
(Summarizer) DISTILBART-CNN-12-6_BIG-decoding-charactersSpeed
(Summarizer) QWEN2.5-0.5B-INSTRUCT_BIG-decoding-charactersSpeed
(Summarizer) DISTILBART-CNN-12-6_BIG-prompt-tokenSpeed
(Summarizer) QWEN2.5-0.5B-INSTRUCT_BIG-prompt-tokenSpeed
(Summarizer) DISTILBART-CNN-12-6_BIG-prompt-charactersSpeed
(Summarizer) QWEN2.5-0.5B-INSTRUCT_BIG-prompt-charactersSpeed
(Autofill) pipeline-ready-latency
(Autofill) initialization-latency
(Autofill) model-run-latency
(Autofill) residual-memory-usage
(Autofill) peak-memory-usage