llama.cpp
ggml: add env var GGML_OP_OFFLOAD_MIN_BATCH
#18535
Merged
Overview
Commits
5
Changes
View On GitHub
Commits
  • ggml: add env var GGML_OP_OFFLOAD_MIN_BATCH
    DocShotgun committed 62 days ago
  • ggml: read GGML_OP_OFFLOAD_MIN_BATCH once and store to dev ctx
    DocShotgun committed 62 days ago
  • cann: forward declaration of device context struct
    DocShotgun committed 62 days ago
  • cann: move offload op check after device context declaration
    DocShotgun committed 62 days ago
  • cuda: fix whitespace
    DocShotgun committed 58 days ago
FAQ Terms Privacy Refunds Impressum
Loading