[TESTS] Use FP32 inference precision, FP16 KV cache precision for pipelines #6389
causal_lm_cpp.yml
on: pull_request
Matrix: cpp-beam_search_causal_lm-ubuntu
cpp-multinomial-greedy_causal_lm-ubuntu
12m 55s
cpp-greedy_causal_lm-windows
29m 15s
cpp-greedy_causal_lm-Qwen-7B-Chat
10m 54s
cpp-beam_search_causal_lm-Qwen1_5-7B-Chat
32m 50s
cpp-beam_search_causal_lm-Phi-2
16m 4s
cpp-beam_search_causal_lm-notus-7b-v1
31m 47s
cpp-speculative_decoding_lm-ubuntu
15m 3s
cpp-prompt_lookup_decoding_lm-ubuntu
12m 19s
cpp-Phi-1_5
9m 16s
cpp-greedy_causal_lm-redpajama-3b-chat
11m 53s
cpp-chat_sample-ubuntu
16m 23s
visual_language_chat_sample-ubuntu-minicpm_v2_6
7m 50s
visual_language_chat_sample-ubuntu-llava_1_5
/
visual_language_chat_sample-ubuntu-llava
31m 17s
visual_language_chat_sample-ubuntu-llava_next
/
visual_language_chat_sample-ubuntu-llava
35m 44s
visual_language_chat_sample-ubuntu-internvl2
24m 12s
cpp-continuous-batching-ubuntu
16m 52s
cpp-continuous-batching-windows
27m 31s
cpp-continuous-batching-macos
20m 13s
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
|