Prefix caching for sequences with embeddings. #9119
causal_lm_cpp.yml
on: pull_request
cpp-greedy_causal_lm-windows
34m 1s
cpp-Phi-1_5
7m 36s
cpp-greedy_causal_lm-redpajama-3b-chat
12m 41s
cpp-chat_sample-ubuntu
15m 36s
visual_language_chat_sample-ubuntu-minicpm_v2_6
8m 22s
visual_language_chat_sample-ubuntu-llava_1_5
/
visual_language_chat_sample-ubuntu-llava
11m 13s
visual_language_chat_sample-ubuntu-llava_next
/
visual_language_chat_sample-ubuntu-llava
12m 56s
visual_language_chat_sample-ubuntu-internvl2
11m 1s
cpp-continuous-batching-ubuntu
13m 1s
cpp-continuous-batching-windows
31m 0s
cpp-continuous-batching-macos
21m 44s