Dynamic KV cache allocation #5963
Triggered via pull request
December 19, 2024 14:34
popovaan
Status
Success
Total duration
36m 19s
Artifacts
–
causal_lm_cpp.yml
on: pull_request
Matrix: cpp-beam_search_causal_lm-ubuntu
cpp-multinomial-greedy_causal_lm-ubuntu
17m 52s
cpp-greedy_causal_lm-windows
34m 53s
cpp-greedy_causal_lm-Qwen-7B-Chat
11m 8s
cpp-beam_search_causal_lm-Qwen1_5-7B-Chat
15m 5s
cpp-beam_search_causal_lm-Phi-2
10m 25s
cpp-beam_search_causal_lm-notus-7b-v1
31m 2s
cpp-speculative_decoding_lm-ubuntu
11m 37s
cpp-prompt_lookup_decoding_lm-ubuntu
9m 54s
cpp-Phi-1_5
8m 46s
cpp-greedy_causal_lm-redpajama-3b-chat
11m 27s
cpp-chat_sample-ubuntu
13m 59s
visual_language_chat_sample-ubuntu-minicpm_v2_6
7m 35s
visual_language_chat_sample-ubuntu-llava_1_5
/
visual_language_chat_sample-ubuntu-llava
29m 42s
visual_language_chat_sample-ubuntu-llava_next
/
visual_language_chat_sample-ubuntu-llava
34m 58s
visual_language_chat_sample-ubuntu-internvl2
14m 14s
cpp-continuous-batching-ubuntu
15m 34s
cpp-continuous-batching-windows
24m 33s
cpp-continuous-batching-macos
26m 52s
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
|