llama.cpp
ggml-cuda: flush legacy pool on OOM and retry
#22155
Merged

ggml-cuda: flush legacy pool on OOM and retry #22155

leonardHONG
leonardHONG ggml-cuda: flush legacy pool on OOM and retry
1ab3ca45
leonardHONG leonardHONG requested a review from IMbackK IMbackK 120 days ago
leonardHONG leonardHONG requested a review 120 days ago
JohannesGaessler
leonardHONG
IMbackK
JohannesGaessler
IMbackK
IMbackK
gaugarg-nv
JohannesGaessler
JohannesGaessler commented on 2026-04-20
IMbackK
leonardHONG
JohannesGaessler
gaugarg-nv
github-actions github-actions added Nvidia GPU
github-actions github-actions added ggml
leonardHONG Address review comments: add explicit sync, update destructor, clean …
aa1c01e7
leonardHONG
JohannesGaessler
JohannesGaessler approved these changes on 2026-04-20
IMbackK
IMbackK approved these changes on 2026-04-20
IMbackK IMbackK merged 97895129 into master 119 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone