Skip to content

[Continious Batching] Speculative decoding based on paged attention #1163

[Continious Batching] Speculative decoding based on paged attention

[Continious Batching] Speculative decoding based on paged attention #1163

Triggered via pull request July 31, 2024 12:53
Status Cancelled
Total duration 4m 32s
Billable time 5m
Artifacts

genai_python_lib.yml

on: pull_request
ubuntu_genai_python_lib
4m 4s
ubuntu_genai_python_lib
macos_genai_python_lib
4m 16s
macos_genai_python_lib
windows_genai_python_lib
3m 55s
windows_genai_python_lib
Fit to window
Zoom out
Zoom in

Annotations

6 errors
windows_genai_python_lib
Canceling since a higher priority waiting request for 'genai_python_lib-speculative_decoding' exists
windows_genai_python_lib
The operation was canceled.
ubuntu_genai_python_lib
Canceling since a higher priority waiting request for 'genai_python_lib-speculative_decoding' exists
ubuntu_genai_python_lib
The operation was canceled.
macos_genai_python_lib
Canceling since a higher priority waiting request for 'genai_python_lib-speculative_decoding' exists
macos_genai_python_lib
The operation was canceled.