Skip to content

[CB] Split token streaming and generation to different threads for all CB based pipelines #6994

[CB] Split token streaming and generation to different threads for all CB based pipelines

[CB] Split token streaming and generation to different threads for all CB based pipelines #6994

Triggered via pull request January 17, 2025 15:24
Status Cancelled
Total duration 2m 11s
Artifacts

causal_lm_cpp.yml

on: pull_request
Matrix: cpp-beam_search_causal_lm-ubuntu
cpp-multinomial-greedy_causal_lm-ubuntu
5s
cpp-multinomial-greedy_causal_lm-ubuntu
cpp-greedy_causal_lm-windows
49s
cpp-greedy_causal_lm-windows
cpp-greedy_causal_lm-Qwen-7B-Chat
36s
cpp-greedy_causal_lm-Qwen-7B-Chat
cpp-beam_search_causal_lm-Qwen1_5-7B-Chat
1m 8s
cpp-beam_search_causal_lm-Qwen1_5-7B-Chat
cpp-beam_search_causal_lm-Phi-2
1m 8s
cpp-beam_search_causal_lm-Phi-2
cpp-beam_search_causal_lm-notus-7b-v1
1m 8s
cpp-beam_search_causal_lm-notus-7b-v1
cpp-speculative_decoding_lm-ubuntu
0s
cpp-speculative_decoding_lm-ubuntu
cpp-prompt_lookup_decoding_lm-ubuntu
35s
cpp-prompt_lookup_decoding_lm-ubuntu
cpp-Phi-1_5
0s
cpp-Phi-1_5
cpp-greedy_causal_lm-redpajama-3b-chat
26s
cpp-greedy_causal_lm-redpajama-3b-chat
cpp-chat_sample-ubuntu
1m 1s
cpp-chat_sample-ubuntu
visual_language_chat_sample-ubuntu-minicpm_v2_6
1m 9s
visual_language_chat_sample-ubuntu-minicpm_v2_6
visual_language_chat_sample-ubuntu-llava_1_5  /  visual_language_chat_sample-ubuntu-llava
24s
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
41s
visual_language_chat_sample-ubuntu-llava_next / visual_language_chat_sample-ubuntu-llava
visual_language_chat_sample-ubuntu-internvl2
1m 3s
visual_language_chat_sample-ubuntu-internvl2
cpp-continuous-batching-ubuntu
0s
cpp-continuous-batching-ubuntu
cpp-continuous-batching-windows
46s
cpp-continuous-batching-windows
cpp-continuous-batching-macos
1m 2s
cpp-continuous-batching-macos
visual_language_chat_sample-ubuntu-qwen2vl
57s
visual_language_chat_sample-ubuntu-qwen2vl
ci/gha_overall_status_causal_lm
0s
ci/gha_overall_status_causal_lm
Fit to window
Zoom out
Zoom in

Annotations

35 errors and 1 warning
cpp-speculative_decoding_lm-ubuntu
Canceling since a higher priority waiting request for 'refs/pull/1544/merge-causal-lm-cpp' exists
cpp-continuous-batching-ubuntu
Canceling since a higher priority waiting request for 'refs/pull/1544/merge-causal-lm-cpp' exists
cpp-Phi-1_5
Canceling since a higher priority waiting request for 'refs/pull/1544/merge-causal-lm-cpp' exists
visual_language_chat_sample-ubuntu-qwen2vl
Canceling since a higher priority waiting request for 'refs/pull/1544/merge-causal-lm-cpp' exists
cpp-continuous-batching-windows
Canceling since a higher priority waiting request for 'refs/pull/1544/merge-causal-lm-cpp' exists
cpp-continuous-batching-windows
The operation was canceled.
cpp-multinomial-greedy_causal_lm-ubuntu
Canceling since a higher priority waiting request for 'refs/pull/1544/merge-causal-lm-cpp' exists
cpp-multinomial-greedy_causal_lm-ubuntu
The operation was canceled.
cpp-greedy_causal_lm-windows
Canceling since a higher priority waiting request for 'refs/pull/1544/merge-causal-lm-cpp' exists
cpp-greedy_causal_lm-windows
The operation was canceled.
visual_language_chat_sample-ubuntu-internvl2
Canceling since a higher priority waiting request for 'refs/pull/1544/merge-causal-lm-cpp' exists
cpp-greedy_causal_lm-Qwen-7B-Chat
Canceling since a higher priority waiting request for 'refs/pull/1544/merge-causal-lm-cpp' exists
cpp-greedy_causal_lm-Qwen-7B-Chat
The operation was canceled.
cpp-beam_search_causal_lm-Qwen1_5-7B-Chat
Canceling since a higher priority waiting request for 'refs/pull/1544/merge-causal-lm-cpp' exists
cpp-beam_search_causal_lm-Qwen1_5-7B-Chat
The operation was canceled.
cpp-beam_search_causal_lm-ubuntu (python ./samples/python/text_generation/beam_search_causal_lm.py)
Canceling since a higher priority waiting request for 'refs/pull/1544/merge-causal-lm-cpp' exists
cpp-prompt_lookup_decoding_lm-ubuntu
Canceling since a higher priority waiting request for 'refs/pull/1544/merge-causal-lm-cpp' exists
cpp-prompt_lookup_decoding_lm-ubuntu
The operation was canceled.
cpp-beam_search_causal_lm-Phi-2
Canceling since a higher priority waiting request for 'refs/pull/1544/merge-causal-lm-cpp' exists
cpp-beam_search_causal_lm-Phi-2
The operation was canceled.
cpp-beam_search_causal_lm-notus-7b-v1
Canceling since a higher priority waiting request for 'refs/pull/1544/merge-causal-lm-cpp' exists
cpp-beam_search_causal_lm-notus-7b-v1
The operation was canceled.
visual_language_chat_sample-ubuntu-llava_next / visual_language_chat_sample-ubuntu-llava
Canceling since a higher priority waiting request for 'refs/pull/1544/merge-causal-lm-cpp' exists
cpp-beam_search_causal_lm-ubuntu (./build/samples/cpp/text_generation/beam_search_causal_lm)
Canceling since a higher priority waiting request for 'refs/pull/1544/merge-causal-lm-cpp' exists
visual_language_chat_sample-ubuntu-llava_1_5 / visual_language_chat_sample-ubuntu-llava
Canceling since a higher priority waiting request for 'refs/pull/1544/merge-causal-lm-cpp' exists
cpp-chat_sample-ubuntu
Canceling since a higher priority waiting request for 'refs/pull/1544/merge-causal-lm-cpp' exists
cpp-chat_sample-ubuntu
The operation was canceled.
visual_language_chat_sample-ubuntu-minicpm_v2_6
Canceling since a higher priority waiting request for 'refs/pull/1544/merge-causal-lm-cpp' exists
cpp-greedy_causal_lm-redpajama-3b-chat
Canceling since a higher priority waiting request for 'refs/pull/1544/merge-causal-lm-cpp' exists
cpp-greedy_causal_lm-redpajama-3b-chat
The operation was canceled.
cpp-continuous-batching-macos
Canceling since a higher priority waiting request for 'refs/pull/1544/merge-causal-lm-cpp' exists
cpp-continuous-batching-macos
The operation was canceled.
ci/gha_overall_status_causal_lm
Process completed with exit code 1.
ci/gha_overall_status_causal_lm
ubuntu-latest pipelines will use ubuntu-24.04 soon. For more details, see https://github.com/actions/runner-images/issues/10636