Dynamic KV cache allocation #6081
Triggered via pull request
December 24, 2024 08:33
popovaan
Status
Success
Total duration
38m 25s
Artifacts
–
causal_lm_cpp.yml
on: pull_request
Matrix: cpp-beam_search_causal_lm-ubuntu
cpp-multinomial-greedy_causal_lm-ubuntu
18m 2s
cpp-greedy_causal_lm-windows
34m 2s
cpp-greedy_causal_lm-Qwen-7B-Chat
11m 18s
cpp-beam_search_causal_lm-Qwen1_5-7B-Chat
33m 3s
cpp-beam_search_causal_lm-Phi-2
16m 39s
cpp-beam_search_causal_lm-notus-7b-v1
31m 29s
cpp-speculative_decoding_lm-ubuntu
13m 2s
cpp-prompt_lookup_decoding_lm-ubuntu
11m 42s
cpp-Phi-1_5
8m 14s
cpp-greedy_causal_lm-redpajama-3b-chat
10m 54s
cpp-chat_sample-ubuntu
13m 39s
visual_language_chat_sample-ubuntu-minicpm_v2_6
8m 12s
visual_language_chat_sample-ubuntu-llava_1_5
/
visual_language_chat_sample-ubuntu-llava
31m 31s
visual_language_chat_sample-ubuntu-llava_next
/
visual_language_chat_sample-ubuntu-llava
36m 26s
visual_language_chat_sample-ubuntu-internvl2
13m 19s
cpp-continuous-batching-ubuntu
15m 28s
cpp-continuous-batching-windows
26m 4s
cpp-continuous-batching-macos
20m 37s
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
|