Skip to content

[CB]: allow int8 KV cache precision for CPU #7496

[CB]: allow int8 KV cache precision for CPU

[CB]: allow int8 KV cache precision for CPU #7496

Triggered via pull request January 30, 2025 14:08
Status Failure
Total duration 33m 26s
Artifacts

causal_lm_cpp.yml

on: pull_request
Matrix: cpp-beam_search_causal_lm-ubuntu
cpp-multinomial-greedy_causal_lm-ubuntu
20m 25s
cpp-multinomial-greedy_causal_lm-ubuntu
cpp-greedy_causal_lm-windows
27m 28s
cpp-greedy_causal_lm-windows
cpp-greedy_causal_lm-Qwen-7B-Chat
10m 37s
cpp-greedy_causal_lm-Qwen-7B-Chat
cpp-beam_search_causal_lm-Qwen1_5-7B-Chat
33m 8s
cpp-beam_search_causal_lm-Qwen1_5-7B-Chat
cpp-beam_search_causal_lm-Phi-2
16m 22s
cpp-beam_search_causal_lm-Phi-2
cpp-beam_search_causal_lm-notus-7b-v1
14m 55s
cpp-beam_search_causal_lm-notus-7b-v1
cpp-speculative_decoding_lm-ubuntu
22m 17s
cpp-speculative_decoding_lm-ubuntu
cpp-prompt_lookup_decoding_lm-ubuntu
11m 16s
cpp-prompt_lookup_decoding_lm-ubuntu
cpp-Phi-1_5
8m 39s
cpp-Phi-1_5
cpp-greedy_causal_lm-redpajama-3b-chat
11m 10s
cpp-greedy_causal_lm-redpajama-3b-chat
cpp-chat_sample-ubuntu
15m 8s
cpp-chat_sample-ubuntu
visual_language_chat_sample-ubuntu-minicpm_v2_6
7m 11s
visual_language_chat_sample-ubuntu-minicpm_v2_6
visual_language_chat_sample-ubuntu-llava_1_5  /  visual_language_chat_sample-ubuntu-llava
30m 42s
visual_language_chat_sample-ubuntu-llava_1_5 / visual_language_chat_sample-ubuntu-llava
visual_language_chat_sample-ubuntu-llava_next  /  visual_language_chat_sample-ubuntu-llava
19m 1s
visual_language_chat_sample-ubuntu-llava_next / visual_language_chat_sample-ubuntu-llava
visual_language_chat_sample-ubuntu-internvl2
13m 4s
visual_language_chat_sample-ubuntu-internvl2
cpp-continuous-batching-ubuntu
14m 53s
cpp-continuous-batching-ubuntu
cpp-continuous-batching-windows
27m 1s
cpp-continuous-batching-windows
cpp-continuous-batching-macos
19m 53s
cpp-continuous-batching-macos
visual_language_chat_sample-ubuntu-qwen2vl
17m 35s
visual_language_chat_sample-ubuntu-qwen2vl
ci/gha_overall_status_causal_lm
0s
ci/gha_overall_status_causal_lm
Fit to window
Zoom out
Zoom in

Annotations

2 errors
cpp-continuous-batching-macos
Process completed with exit code 124.
ci/gha_overall_status_causal_lm
Process completed with exit code 1.