Georgi Gerganov
ac261bea66
test-thread-safety : handle tiny training context of the input model
2025-10-29 16:10:07 +02:00
Acly
d8eaa26e4d
tests : fix test-thread-safety when compiling with multiple backends ( #16699 )
...
* run one test per backend/device (even if it's the same device)
2025-10-22 12:01:22 +02:00
Georgi Gerganov
00131d6eaf
tests : update for LLAMA_SET_ROWS=1 ( #14961 )
...
* test-thread-safety : each context uses a single sequence
* embedding : handle --parallel argument
ggml-ci
* save-load : handle -np 1
ggml-ci
* thread-safety : avoid overriding threads, reduce test case arg
ggml-ci
2025-07-30 15:12:02 +03:00
Diego Devesa
6adc3c3ebc
llama : add thread safety test ( #14035 )
...
* llama : add thread safety test
* llamafile : remove global state
* llama : better LLAMA_SPLIT_MODE_NONE logic
when main_gpu < 0 GPU devices are not used
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
2025-06-16 08:11:43 -07:00
