[CPU] Change kvcache default type of PagedAttention to u8 for CPU plugin #6400
causal_lm_cpp.yml
on: pull_request
Matrix: cpp-beam_search_causal_lm-ubuntu
cpp-multinomial-greedy_causal_lm-ubuntu
14m 19s
cpp-greedy_causal_lm-windows
26m 25s
cpp-greedy_causal_lm-Qwen-7B-Chat
11m 14s
cpp-beam_search_causal_lm-Qwen1_5-7B-Chat
16m 20s
cpp-beam_search_causal_lm-Phi-2
9m 58s
cpp-beam_search_causal_lm-notus-7b-v1
15m 16s
cpp-speculative_decoding_lm-ubuntu
13m 33s
cpp-prompt_lookup_decoding_lm-ubuntu
11m 17s
cpp-Phi-1_5
8m 19s
cpp-greedy_causal_lm-redpajama-3b-chat
11m 24s
cpp-chat_sample-ubuntu
13m 50s
visual_language_chat_sample-ubuntu-minicpm_v2_6
8m 37s
visual_language_chat_sample-ubuntu-llava_1_5
/
visual_language_chat_sample-ubuntu-llava
14m 13s
visual_language_chat_sample-ubuntu-llava_next
/
visual_language_chat_sample-ubuntu-llava
18m 36s
visual_language_chat_sample-ubuntu-internvl2
14m 50s
cpp-continuous-batching-ubuntu
14m 37s
cpp-continuous-batching-windows
23m 56s
cpp-continuous-batching-macos
24m 53s
ci/gha_overall_status_causal_lm
0s
Annotations
2 errors and 1 warning
cpp-speculative_decoding_lm-ubuntu
Process completed with exit code 1.
|
ci/gha_overall_status_causal_lm
Process completed with exit code 1.
|
ci/gha_overall_status_causal_lm
ubuntu-latest pipelines will use ubuntu-24.04 soon. For more details, see https://github.com/actions/runner-images/issues/10636
|