Skip to content
causal_lm_cpp

[Speculative decoding] Fix draft_model tun in case of long prompt (#1… #8

Sign in to view logs

[Speculative decoding] Fix draft_model tun in case of long prompt (#1…

[Speculative decoding] Fix draft_model tun in case of long prompt (#1… #8

Run time

Learn about OS pricing on GitHub Actions
Job Run time
cpp-beam_search_causal_lm-notus-7b-v1
1s
cpp-beam_search_causal_lm-Phi-2
1s
cpp-beam_search_causal_lm-Qwen1_5-7B-Chat
1s
cpp-beam_search_causal_lm-ubuntu (./build/samples/cpp/beam_search_causal_lm/beam_search_causal_lm)
17m 52s
cpp-beam_search_causal_lm-ubuntu (python ./samples/python/beam_search_causal_lm/beam_search_causa...
18m 6s
cpp-chat_sample-ubuntu
14m 1s
cpp-continuous-batching-macos
15m 44s
cpp-continuous-batching-ubuntu
1s
cpp-continuous-batching-windows
27m 4s
cpp-greedy_causal_lm-Qwen-7B-Chat
1s
cpp-greedy_causal_lm-redpajama-3b-chat
1s
cpp-greedy_causal_lm-windows
35m 20s
cpp-multinomial-greedy_causal_lm-ubuntu
1s
cpp-Phi-1_5
1s
cpp-prompt_lookup_decoding_lm-ubuntu
1s
cpp-speculative_decoding_lm-ubuntu
1s
visual_language_chat_sample-ubuntu
1s
ci/gha_overall_status_causal_lm
1s
2h 8m 19s