Harald Hoyer
ac70c57c15
Preload Qwen3.6-27B and Qwen3.6-35B-A3B at startup (load-on-startup) so both are warm immediately under --models-max 2, set parallel = 1 as the [*] fallback for any other model, and adjust per-model context size and draft depth.
35 lines
854 B
INI
35 lines
854 B
INI
version = 1
|
|
|
|
[*]
|
|
flash-attn = on
|
|
parallel = 1
|
|
jinja = true
|
|
n-gpu-layers = 99
|
|
threads = 8
|
|
ubatch-size = 256
|
|
cache-type-k = bf16
|
|
cache-type-v = bf16
|
|
temp = 0.6
|
|
top-p = 0.95
|
|
top-k = 20
|
|
min-p = 0.0
|
|
mmap = false
|
|
no-context-shift = true
|
|
chat-template-kwargs = {"preserve_thinking": true}
|
|
fit = on
|
|
spec-type = draft-mtp
|
|
|
|
[Qwen3.6-35B-A3B]
|
|
hf = unsloth/Qwen3.6-35B-A3B-MTP-GGUF:UD-Q8_K_XL
|
|
spec-draft-n-max = 2
|
|
parallel = 1
|
|
c = 131072
|
|
load-on-startup = true
|
|
|
|
[Qwen3.6-27B]
|
|
hf = unsloth/Qwen3.6-27B-MTP-GGUF:Q6_K
|
|
spec-draft-n-max = 6
|
|
parallel = 2
|
|
c = 524288
|
|
load-on-startup = true
|
|
|