Add parametrization for the detokenization/decoding #4772
Triggered via pull request
November 25, 2024 11:44
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 4s
cpp-greedy_causal_lm-windows
25m 43s
cpp-greedy_causal_lm-Qwen-7B-Chat
9m 48s
cpp-beam_search_causal_lm-Qwen1_5-7B-Chat
14m 54s
cpp-beam_search_causal_lm-Phi-2
10m 51s
cpp-beam_search_causal_lm-notus-7b-v1
14m 44s
cpp-speculative_decoding_lm-ubuntu
12m 8s
cpp-prompt_lookup_decoding_lm-ubuntu
15m 0s
cpp-Phi-1_5
7m 15s
cpp-greedy_causal_lm-redpajama-3b-chat
17m 14s
cpp-chat_sample-ubuntu
14m 26s
visual_language_chat_sample-ubuntu-minicpm_v2_6
7m 36s
visual_language_chat_sample-ubuntu-llava_1_5
/
visual_language_chat_sample-ubuntu-llava
30m 28s
visual_language_chat_sample-ubuntu-llava_next
/
visual_language_chat_sample-ubuntu-llava
34m 50s
visual_language_chat_sample-ubuntu-internvl2
22m 32s
cpp-continuous-batching-ubuntu
14m 39s
cpp-continuous-batching-windows
23m 45s
cpp-continuous-batching-macos
21m 31s
ci/gha_overall_status_causal_lm
0s
Annotations
20 warnings