aboutsummaryrefslogtreecommitdiff
path: root/examples
diff options
context:
space:
mode:
authorGeorgi Gerganov <ggerganov@gmail.com>2023-03-24 23:17:37 +0200
committerGitHub <noreply@github.com>2023-03-24 23:17:37 +0200
commit7a9b6c3a8bdc1cb75fefc826dfaa7331eb63695d (patch)
tree339815189c912e9a759a0259613621f6a2adcbf4 /examples
parent31572d966531f7d768eb773322016ab78eb6e835 (diff)
Reduce memory usage and allocate enough memory for largest context (#473)
* Reduce memory usage and allocate enough memory for large contexts * Simpler scratch buffer usage * Reenable BLAS for quantized mul_mat * Fix number of layers in 30B and 65B * Fix KV cache size for F32
Diffstat (limited to 'examples')
0 files changed, 0 insertions, 0 deletions