Skip to content

Dynamic KV cache allocation #6098

Dynamic KV cache allocation

Dynamic KV cache allocation #6098

Triggered via pull request December 24, 2024 13:30
Status Cancelled
Total duration 44s
Artifacts

causal_lm_cpp.yml

on: pull_request
Matrix: cpp-beam_search_causal_lm-ubuntu
cpp-multinomial-greedy_causal_lm-ubuntu
28s
cpp-multinomial-greedy_causal_lm-ubuntu
cpp-greedy_causal_lm-windows
4s
cpp-greedy_causal_lm-windows
cpp-greedy_causal_lm-Qwen-7B-Chat
0s
cpp-greedy_causal_lm-Qwen-7B-Chat
cpp-beam_search_causal_lm-Qwen1_5-7B-Chat
0s
cpp-beam_search_causal_lm-Qwen1_5-7B-Chat
cpp-beam_search_causal_lm-Phi-2
16s
cpp-beam_search_causal_lm-Phi-2
cpp-beam_search_causal_lm-notus-7b-v1
21s
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
0s
cpp-prompt_lookup_decoding_lm-ubuntu
cpp-Phi-1_5
0s
cpp-Phi-1_5
cpp-greedy_causal_lm-redpajama-3b-chat
28s
cpp-greedy_causal_lm-redpajama-3b-chat
cpp-chat_sample-ubuntu
20s
cpp-chat_sample-ubuntu
visual_language_chat_sample-ubuntu-minicpm_v2_6
29s
visual_language_chat_sample-ubuntu-minicpm_v2_6
visual_language_chat_sample-ubuntu-llava_1_5  /  visual_language_chat_sample-ubuntu-llava
0s
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
0s
visual_language_chat_sample-ubuntu-llava_next / visual_language_chat_sample-ubuntu-llava
visual_language_chat_sample-ubuntu-internvl2
19s
visual_language_chat_sample-ubuntu-internvl2
cpp-continuous-batching-ubuntu
27s
cpp-continuous-batching-ubuntu
cpp-continuous-batching-windows
0s
cpp-continuous-batching-windows
cpp-continuous-batching-macos
7s
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

31 errors and 1 warning
cpp-beam_search_causal_lm-Qwen1_5-7B-Chat
Canceling since a higher priority waiting request for 'refs/pull/1364/merge-causal-lm-cpp' exists
cpp-greedy_causal_lm-Qwen-7B-Chat
Canceling since a higher priority waiting request for 'refs/pull/1364/merge-causal-lm-cpp' exists
cpp-Phi-1_5
Canceling since a higher priority waiting request for 'refs/pull/1364/merge-causal-lm-cpp' exists
cpp-speculative_decoding_lm-ubuntu
Canceling since a higher priority waiting request for 'refs/pull/1364/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/1364/merge-causal-lm-cpp' exists
cpp-prompt_lookup_decoding_lm-ubuntu
Canceling since a higher priority waiting request for 'refs/pull/1364/merge-causal-lm-cpp' exists
visual_language_chat_sample-ubuntu-llava_next / visual_language_chat_sample-ubuntu-llava
Canceling since a higher priority waiting request for 'refs/pull/1364/merge-causal-lm-cpp' exists
cpp-continuous-batching-windows
Canceling since a higher priority waiting request for 'refs/pull/1364/merge-causal-lm-cpp' exists
cpp-beam_search_causal_lm-Phi-2
Canceling since a higher priority waiting request for 'refs/pull/1364/merge-causal-lm-cpp' exists
cpp-beam_search_causal_lm-Phi-2
The operation was canceled.
cpp-greedy_causal_lm-windows
Canceling since a higher priority waiting request for 'refs/pull/1364/merge-causal-lm-cpp' exists
cpp-greedy_causal_lm-windows
The operation was canceled.
cpp-continuous-batching-macos
Canceling since a higher priority waiting request for 'refs/pull/1364/merge-causal-lm-cpp' exists
cpp-continuous-batching-macos
The operation was canceled.
visual_language_chat_sample-ubuntu-internvl2
Canceling since a higher priority waiting request for 'refs/pull/1364/merge-causal-lm-cpp' exists
cpp-beam_search_causal_lm-notus-7b-v1
Canceling since a higher priority waiting request for 'refs/pull/1364/merge-causal-lm-cpp' exists
cpp-beam_search_causal_lm-notus-7b-v1
The operation was canceled.
cpp-beam_search_causal_lm-ubuntu (python ./samples/python/beam_search_causal_lm/beam_search_causa...
Canceling since a higher priority waiting request for 'refs/pull/1364/merge-causal-lm-cpp' exists
cpp-beam_search_causal_lm-ubuntu (./build/samples/cpp/beam_search_causal_lm/beam_search_causal_lm)
Canceling since a higher priority waiting request for 'refs/pull/1364/merge-causal-lm-cpp' exists
cpp-greedy_causal_lm-redpajama-3b-chat
Canceling since a higher priority waiting request for 'refs/pull/1364/merge-causal-lm-cpp' exists
cpp-greedy_causal_lm-redpajama-3b-chat
The operation was canceled.
cpp-multinomial-greedy_causal_lm-ubuntu
Canceling since a higher priority waiting request for 'refs/pull/1364/merge-causal-lm-cpp' exists
cpp-multinomial-greedy_causal_lm-ubuntu
The operation was canceled.
cpp-continuous-batching-ubuntu
Canceling since a higher priority waiting request for 'refs/pull/1364/merge-causal-lm-cpp' exists
cpp-continuous-batching-ubuntu
The operation was canceled.
visual_language_chat_sample-ubuntu-minicpm_v2_6
Canceling since a higher priority waiting request for 'refs/pull/1364/merge-causal-lm-cpp' exists
cpp-chat_sample-ubuntu
Canceling since a higher priority waiting request for 'refs/pull/1364/merge-causal-lm-cpp' exists
cpp-chat_sample-ubuntu
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