Dynamic KV cache allocation #6106
Triggered via pull request
December 24, 2024 15:21
ilya-lavrenov
Status
Success
Total duration
37m 33s
Artifacts
–
causal_lm_cpp.yml
on: pull_request
Matrix: cpp-beam_search_causal_lm-ubuntu
cpp-multinomial-greedy_causal_lm-ubuntu
18m 11s
cpp-greedy_causal_lm-windows
26m 27s
cpp-greedy_causal_lm-Qwen-7B-Chat
10m 50s
cpp-beam_search_causal_lm-Qwen1_5-7B-Chat
15m 19s
cpp-beam_search_causal_lm-Phi-2
16m 56s
cpp-beam_search_causal_lm-notus-7b-v1
14m 58s
cpp-speculative_decoding_lm-ubuntu
12m 30s
cpp-prompt_lookup_decoding_lm-ubuntu
11m 28s
cpp-Phi-1_5
8m 16s
cpp-greedy_causal_lm-redpajama-3b-chat
10m 50s
cpp-chat_sample-ubuntu
18m 30s
visual_language_chat_sample-ubuntu-minicpm_v2_6
8m 20s
visual_language_chat_sample-ubuntu-llava_1_5
/
visual_language_chat_sample-ubuntu-llava
30m 50s
visual_language_chat_sample-ubuntu-llava_next
/
visual_language_chat_sample-ubuntu-llava
36m 4s
visual_language_chat_sample-ubuntu-internvl2
14m 47s
cpp-continuous-batching-ubuntu
16m 16s
cpp-continuous-batching-windows
26m 24s
cpp-continuous-batching-macos
21m 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
|