Fix wrong token latency when batch size is greater than 1 #4708
Triggered via pull request
November 21, 2024 10:43
Status
Success
Total duration
34m 39s
Artifacts
–
causal_lm_cpp.yml
on: pull_request
Matrix: cpp-beam_search_causal_lm-ubuntu
cpp-multinomial-greedy_causal_lm-ubuntu
13m 22s
cpp-greedy_causal_lm-windows
24m 30s
cpp-greedy_causal_lm-Qwen-7B-Chat
10m 18s
cpp-beam_search_causal_lm-Qwen1_5-7B-Chat
33m 14s
cpp-beam_search_causal_lm-Phi-2
16m 5s
cpp-beam_search_causal_lm-notus-7b-v1
14m 36s
cpp-speculative_decoding_lm-ubuntu
12m 13s
cpp-prompt_lookup_decoding_lm-ubuntu
14m 57s
cpp-Phi-1_5
7m 42s
cpp-greedy_causal_lm-redpajama-3b-chat
15m 51s
cpp-chat_sample-ubuntu
14m 19s
visual_language_chat_sample-ubuntu-minicpm_v2_6
7m 56s
visual_language_chat_sample-ubuntu-llava_1_5
/
visual_language_chat_sample-ubuntu-llava
31m 22s
visual_language_chat_sample-ubuntu-llava_next
/
visual_language_chat_sample-ubuntu-llava
18m 30s
visual_language_chat_sample-ubuntu-internvl2
14m 8s
cpp-continuous-batching-ubuntu
15m 1s
cpp-continuous-batching-windows
25m 18s
cpp-continuous-batching-macos
19m 16s
ci/gha_overall_status_causal_lm
0s
Annotations
20 warnings