Skip to content
causal_lm_cpp

Add speculative decoding params to lm_bench #4630

Sign in to view logs

Add speculative decoding params to lm_bench

Add speculative decoding params to lm_bench #4630

Triggered via pull request November 20, 2024 05:51
@eaidovaeaidova
synchronize #1221
sbalandi:llm_bench_sd
Status Success
Total duration 41m 37s
Artifacts –

causal_lm_cpp.yml

on: pull_request
Matrix: cpp-beam_search_causal_lm-ubuntu
cpp-multinomial-greedy_causal_lm-ubuntu
17m 37s
cpp-multinomial-greedy_causal_lm-ubuntu
cpp-greedy_causal_lm-windows
26m 6s
cpp-greedy_causal_lm-windows
cpp-greedy_causal_lm-Qwen-7B-Chat
10m 22s
cpp-greedy_causal_lm-Qwen-7B-Chat
cpp-beam_search_causal_lm-Qwen1_5-7B-Chat
14m 19s
cpp-beam_search_causal_lm-Qwen1_5-7B-Chat
cpp-beam_search_causal_lm-Phi-2
10m 13s
cpp-beam_search_causal_lm-Phi-2
cpp-beam_search_causal_lm-notus-7b-v1
31m 5s
cpp-beam_search_causal_lm-notus-7b-v1
cpp-speculative_decoding_lm-ubuntu
12m 33s
cpp-speculative_decoding_lm-ubuntu
cpp-prompt_lookup_decoding_lm-ubuntu
12m 37s
cpp-prompt_lookup_decoding_lm-ubuntu
cpp-Phi-1_5
7m 39s
cpp-Phi-1_5
cpp-greedy_causal_lm-redpajama-3b-chat
14m 31s
cpp-greedy_causal_lm-redpajama-3b-chat
cpp-chat_sample-ubuntu
14m 5s
cpp-chat_sample-ubuntu
visual_language_chat_sample-ubuntu-minicpm_v2_6
6m 46s
visual_language_chat_sample-ubuntu-minicpm_v2_6
visual_language_chat_sample-ubuntu-llava_1_5  /  visual_language_chat_sample-ubuntu-llava
13m 35s
visual_language_chat_sample-ubuntu-llava_1_5 / visual_language_chat_sample-ubuntu-llava
visual_language_chat_sample-ubuntu-llava_next  /  visual_language_chat_sample-ubuntu-llava
35m 12s
visual_language_chat_sample-ubuntu-llava_next / visual_language_chat_sample-ubuntu-llava
visual_language_chat_sample-ubuntu-internvl2
40m 19s
visual_language_chat_sample-ubuntu-internvl2
cpp-continuous-batching-ubuntu
14m 58s
cpp-continuous-batching-ubuntu
cpp-continuous-batching-windows
23m 0s
cpp-continuous-batching-windows
cpp-continuous-batching-macos
21m 54s
cpp-continuous-batching-macos
ci/gha_overall_status_causal_lm
0s
ci/gha_overall_status_causal_lm
Fit to window
Zoom out
Zoom in

Annotations

20 warnings
visual_language_chat_sample-ubuntu-minicpm_v2_6
The following actions use a deprecated Node.js version and will be forced to run on node20: actions/setup-python@v4. For more info: https://github.blog/changelog/2024-03-07-github-actions-all-actions-will-run-on-node20-instead-of-node16-by-default/
cpp-Phi-1_5
The following actions use a deprecated Node.js version and will be forced to run on node20: actions/setup-python@v4. For more info: https://github.blog/changelog/2024-03-07-github-actions-all-actions-will-run-on-node20-instead-of-node16-by-default/
cpp-beam_search_causal_lm-Phi-2
The following actions use a deprecated Node.js version and will be forced to run on node20: actions/setup-python@v4. For more info: https://github.blog/changelog/2024-03-07-github-actions-all-actions-will-run-on-node20-instead-of-node16-by-default/
cpp-greedy_causal_lm-Qwen-7B-Chat
The following actions use a deprecated Node.js version and will be forced to run on node20: actions/setup-python@v4. For more info: https://github.blog/changelog/2024-03-07-github-actions-all-actions-will-run-on-node20-instead-of-node16-by-default/
cpp-speculative_decoding_lm-ubuntu
The following actions use a deprecated Node.js version and will be forced to run on node20: actions/setup-python@v4. For more info: https://github.blog/changelog/2024-03-07-github-actions-all-actions-will-run-on-node20-instead-of-node16-by-default/
cpp-prompt_lookup_decoding_lm-ubuntu
The following actions use a deprecated Node.js version and will be forced to run on node20: actions/setup-python@v4. For more info: https://github.blog/changelog/2024-03-07-github-actions-all-actions-will-run-on-node20-instead-of-node16-by-default/
cpp-chat_sample-ubuntu
The following actions use a deprecated Node.js version and will be forced to run on node20: actions/setup-python@v4. For more info: https://github.blog/changelog/2024-03-07-github-actions-all-actions-will-run-on-node20-instead-of-node16-by-default/
cpp-beam_search_causal_lm-Qwen1_5-7B-Chat
The following actions use a deprecated Node.js version and will be forced to run on node20: actions/setup-python@v4. For more info: https://github.blog/changelog/2024-03-07-github-actions-all-actions-will-run-on-node20-instead-of-node16-by-default/
cpp-greedy_causal_lm-redpajama-3b-chat
The following actions use a deprecated Node.js version and will be forced to run on node20: actions/setup-python@v4. For more info: https://github.blog/changelog/2024-03-07-github-actions-all-actions-will-run-on-node20-instead-of-node16-by-default/
visual_language_chat_sample-ubuntu-llava_1_5 / visual_language_chat_sample-ubuntu-llava
The following actions use a deprecated Node.js version and will be forced to run on node20: actions/setup-python@v4. For more info: https://github.blog/changelog/2024-03-07-github-actions-all-actions-will-run-on-node20-instead-of-node16-by-default/
cpp-continuous-batching-ubuntu
The following actions use a deprecated Node.js version and will be forced to run on node20: actions/setup-python@v4. For more info: https://github.blog/changelog/2024-03-07-github-actions-all-actions-will-run-on-node20-instead-of-node16-by-default/
cpp-beam_search_causal_lm-ubuntu (python ./samples/python/beam_search_causal_lm/beam_search_causa...
The following actions use a deprecated Node.js version and will be forced to run on node20: actions/setup-python@v4. For more info: https://github.blog/changelog/2024-03-07-github-actions-all-actions-will-run-on-node20-instead-of-node16-by-default/
cpp-beam_search_causal_lm-ubuntu (./build/samples/cpp/beam_search_causal_lm/beam_search_causal_lm)
The following actions use a deprecated Node.js version and will be forced to run on node20: actions/setup-python@v4. For more info: https://github.blog/changelog/2024-03-07-github-actions-all-actions-will-run-on-node20-instead-of-node16-by-default/
cpp-multinomial-greedy_causal_lm-ubuntu
The following actions use a deprecated Node.js version and will be forced to run on node20: actions/setup-python@v4. For more info: https://github.blog/changelog/2024-03-07-github-actions-all-actions-will-run-on-node20-instead-of-node16-by-default/
cpp-continuous-batching-macos
The following actions use a deprecated Node.js version and will be forced to run on node20: actions/setup-python@v4. For more info: https://github.blog/changelog/2024-03-07-github-actions-all-actions-will-run-on-node20-instead-of-node16-by-default/
cpp-continuous-batching-windows
The following actions use a deprecated Node.js version and will be forced to run on node20: actions/setup-python@v4. For more info: https://github.blog/changelog/2024-03-07-github-actions-all-actions-will-run-on-node20-instead-of-node16-by-default/
cpp-greedy_causal_lm-windows
The following actions use a deprecated Node.js version and will be forced to run on node20: actions/setup-python@v4. For more info: https://github.blog/changelog/2024-03-07-github-actions-all-actions-will-run-on-node20-instead-of-node16-by-default/
cpp-beam_search_causal_lm-notus-7b-v1
The following actions use a deprecated Node.js version and will be forced to run on node20: actions/setup-python@v4. For more info: https://github.blog/changelog/2024-03-07-github-actions-all-actions-will-run-on-node20-instead-of-node16-by-default/
visual_language_chat_sample-ubuntu-llava_next / visual_language_chat_sample-ubuntu-llava
The following actions use a deprecated Node.js version and will be forced to run on node20: actions/setup-python@v4. For more info: https://github.blog/changelog/2024-03-07-github-actions-all-actions-will-run-on-node20-instead-of-node16-by-default/
visual_language_chat_sample-ubuntu-internvl2
The following actions use a deprecated Node.js version and will be forced to run on node20: actions/setup-python@v4. For more info: https://github.blog/changelog/2024-03-07-github-actions-all-actions-will-run-on-node20-instead-of-node16-by-default/