Gahow Wang 6ce21345be cuda: add cached_trim() to release pooled GPU buffers ...

Exposes the caching allocator's trim() through a public free function.
Called after weight fusion during model loading to free temporary buffers
that would otherwise sit in the pool and cause OOM.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-05-30 12:50:04 +08:00

..

src

cuda: add cached_trim() to release pooled GPU buffers

2026-05-30 12:50:04 +08:00

tests

phase 0+1: fix Rust 2024 edition compat + memory query

2026-05-21 19:40:49 +08:00

build.rs

phase 0+1: project scaffold + xserv-cuda crate

2026-05-21 18:40:22 +08:00

Cargo.toml

phase 0+1: fix Rust 2024 edition compat + memory query

2026-05-21 19:40:49 +08:00