Dynamic KV cache allocation #6096
Triggered via pull request
December 24, 2024 12:50
popovaan
Status
Success
Total duration
36m 33s
Artifacts
–
causal_lm_cpp.yml
on: pull_request
Matrix: cpp-beam_search_causal_lm-ubuntu
cpp-multinomial-greedy_causal_lm-ubuntu
13m 59s
cpp-greedy_causal_lm-windows
27m 47s
cpp-greedy_causal_lm-Qwen-7B-Chat
10m 45s
cpp-beam_search_causal_lm-Qwen1_5-7B-Chat
32m 50s
cpp-beam_search_causal_lm-Phi-2
15m 57s
cpp-beam_search_causal_lm-notus-7b-v1
14m 28s
cpp-speculative_decoding_lm-ubuntu
13m 12s
cpp-prompt_lookup_decoding_lm-ubuntu
11m 27s
cpp-Phi-1_5
8m 13s
cpp-greedy_causal_lm-redpajama-3b-chat
11m 27s
cpp-chat_sample-ubuntu
13m 43s
visual_language_chat_sample-ubuntu-minicpm_v2_6
8m 56s
visual_language_chat_sample-ubuntu-llava_1_5
/
visual_language_chat_sample-ubuntu-llava
13m 44s
visual_language_chat_sample-ubuntu-llava_next
/
visual_language_chat_sample-ubuntu-llava
34m 59s
visual_language_chat_sample-ubuntu-internvl2
24m 11s
cpp-continuous-batching-ubuntu
15m 42s
cpp-continuous-batching-windows
22m 40s
cpp-continuous-batching-macos
29m 4s
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
|