Akarshan Biswas e80a865def

fix: detect allocation failures as out-of-memory errors (#6459) ...

The Llama.cpp backend can emit the phrase “failed to allocate” when it runs out of memory.
Adding this check ensures such messages are correctly classified as out‑of‑memory errors,
providing more accurate error handling CPU backends.

2025-09-15 12:35:24 +05:30

..

gguf

feat: Add model compatibility check and memory estimation (#6243)

2025-08-21 16:13:50 +05:30

cleanup.rs

Backend Architecture Refactoring (#6094) (#6162)

2025-08-15 08:59:01 +07:00

commands.rs

feat: Add support for custom environmental variables to llama.cpp (#6256)

2025-08-21 15:50:37 +05:30

device.rs

feat: improve testing (#6395)

2025-09-09 12:16:25 +07:00

error.rs

fix: detect allocation failures as out-of-memory errors (#6459)

2025-09-15 12:35:24 +05:30

lib.rs

Backend Architecture Refactoring (#6094) (#6162)

2025-08-15 08:59:01 +07:00

path.rs

refactor: moved get_short_path to utils and use it in decompress

2025-09-11 09:52:10 +05:30

process.rs

Backend Architecture Refactoring (#6094) (#6162)

2025-08-15 08:59:01 +07:00

state.rs

Backend Architecture Refactoring (#6094) (#6162)

2025-08-15 08:59:01 +07:00