Dynamic KV cache allocation #6071
Triggered via pull request
December 23, 2024 15:59
popovaan
Status
Success
Total duration
37m 28s
Artifacts
–
causal_lm_cpp.yml
on: pull_request
Matrix: cpp-beam_search_causal_lm-ubuntu
cpp-multinomial-greedy_causal_lm-ubuntu
18m 19s
cpp-greedy_causal_lm-windows
27m 29s
cpp-greedy_causal_lm-Qwen-7B-Chat
11m 14s
cpp-beam_search_causal_lm-Qwen1_5-7B-Chat
15m 30s
cpp-beam_search_causal_lm-Phi-2
16m 21s
cpp-beam_search_causal_lm-notus-7b-v1
14m 32s
cpp-speculative_decoding_lm-ubuntu
12m 16s
cpp-prompt_lookup_decoding_lm-ubuntu
9m 0s
cpp-Phi-1_5
8m 25s
cpp-greedy_causal_lm-redpajama-3b-chat
10m 35s
cpp-chat_sample-ubuntu
15m 28s
visual_language_chat_sample-ubuntu-minicpm_v2_6
8m 13s
visual_language_chat_sample-ubuntu-llava_1_5
/
visual_language_chat_sample-ubuntu-llava
31m 3s
visual_language_chat_sample-ubuntu-llava_next
/
visual_language_chat_sample-ubuntu-llava
35m 54s
visual_language_chat_sample-ubuntu-internvl2
24m 23s
cpp-continuous-batching-ubuntu
15m 9s
cpp-continuous-batching-windows
23m 8s
cpp-continuous-batching-macos
17m 15s
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
|