llama : refactor llama_kv_cache, llama_context and llm_build_context #11275
Triggered via pull request
February 28, 2025 14:29
ggerganov
Status
Cancelled
Total duration
2m 28s
Artifacts
–
server.yml
on: pull_request
server-windows
3s
Matrix: server
Annotations
7 errors
|
server (ADDRESS, RelWithDebInfo)
Canceling since a higher priority waiting request for Server-refs/pull/11213/merge-gg/llama-kv-cache exists
|
|
server (Release)
Canceling since a higher priority waiting request for Server-refs/pull/11213/merge-gg/llama-kv-cache exists
|
|
server-windows
The operation was canceled.
|
|
server-windows
Canceling since a higher priority waiting request for Server-refs/pull/11213/merge-gg/llama-kv-cache exists
|
|
server (UNDEFINED, RelWithDebInfo)
The operation was canceled.
|
|
server (UNDEFINED, RelWithDebInfo)
Canceling since a higher priority waiting request for Server-refs/pull/11213/merge-gg/llama-kv-cache exists
|
|
Server
Canceling since a higher priority waiting request for Server-refs/pull/11213/merge-gg/llama-kv-cache exists
|