[TESTS] Use FP32 inference precision, FP16 KV cache precision for pipelines #6382
Wovchenacausal_lm_cpp.yml
on: pull_request
Matrix: cpp-beam_search_causal_lm-ubuntu
cpp-multinomial-greedy_causal_lm-ubuntu
18m 6s
cpp-greedy_causal_lm-windows
27m 11s
cpp-greedy_causal_lm-Qwen-7B-Chat
11m 23s
cpp-beam_search_causal_lm-Qwen1_5-7B-Chat
15m 12s
cpp-beam_search_causal_lm-Phi-2
10m 27s
cpp-beam_search_causal_lm-notus-7b-v1
14m 37s
cpp-speculative_decoding_lm-ubuntu
13m 39s
cpp-prompt_lookup_decoding_lm-ubuntu
12m 5s
cpp-Phi-1_5
9m 11s
cpp-greedy_causal_lm-redpajama-3b-chat
11m 4s
cpp-chat_sample-ubuntu
13m 54s
visual_language_chat_sample-ubuntu-minicpm_v2_6
7m 45s
visual_language_chat_sample-ubuntu-llava_1_5
/
visual_language_chat_sample-ubuntu-llava
13m 5s
visual_language_chat_sample-ubuntu-llava_next
/
visual_language_chat_sample-ubuntu-llava
36m 29s
visual_language_chat_sample-ubuntu-internvl2
14m 32s
cpp-continuous-batching-ubuntu
13m 39s
cpp-continuous-batching-windows
24m 13s
cpp-continuous-batching-macos
21m 16s
ci/gha_overall_status_causal_lm
0s
Annotations
1 warning
|
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
|