straylight: llama.cpp 0.4.1 preset: no-mmap -> load-mode = none
0.4.1 dropped the no-mmap option (router refused to start: "option 'no-mmap' not recognized in preset '*'"); --load-mode none is the equivalent. All other preset keys checked against 0.4.1's option list. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -19,7 +19,8 @@ let
|
||||
cache-type-k = q8_0
|
||||
cache-type-v = q8_0
|
||||
n-gpu-layers = 999
|
||||
no-mmap = true
|
||||
; llama.cpp 0.4.1 folded --no-mmap into --load-mode (none = read into memory, no mmap)
|
||||
load-mode = none
|
||||
; llama.cpp splits ctx-size across parallel slots: 262144 / 2 = 131072 per slot.
|
||||
ctx-size = 262144
|
||||
parallel = 2
|
||||
|
||||
Reference in New Issue
Block a user