Apply todo, initialize detokenizer's cache #1485
causal_lm_cpp.yml
on: pull_request
cpp-multinomial-greedy_causal_lm-ubuntu
8m 12s
cpp-greedy_causal_lm-windows
18m 17s
cpp-beam_search_causal_lm-Qwen-7B-Chat
10m 10s
cpp-beam_search_causal_lm-Qwen1_5-7B-Chat
7m 39s
cpp-beam_search_causal_lm-Phi-2
7m 26s
cpp-beam_search_causal_lm-notus-7b-v1
7m 35s
cpp-speculative_decoding_lm-ubuntu
10m 39s
cpp-prompt_lookup_decoding_lm-ubuntu
6m 45s
cpp-Phi-1_5
7m 47s
cpp-greedy_causal_lm-redpajama-3b-chat
12m 12s
cpp-chat_sample-ubuntu
9m 25s
cpp-continuous-batching-ubuntu
10m 54s
cpp-continuous-batching-windows
18m 37s
cpp-continuous-batching-macos
15m 37s
Matrix: cpp-beam_search_causal_lm-ubuntu
Annotations
16 warnings