feat: frank-default-large → llama.cpp Qwen3.6-27B Q8_K_P + DFlash draft + ngram-mod (bench pending)
This commit is contained in:
1 parent
a74c1c5bcb
commit
aa2f4bfe39
5 files changed
+268
-4
No files matched your search
@@ -1,16 +1,15 @@
|
||||
[Unit]
|
||||
Description=vLLM Ling-3.0-flash INT4 (CIRU gfx1151) -- frank-default-large
|
||||
Description=llama.cpp Qwen3.6-27B Q8_K_P DFlash+ngram-mod (frank-default-large)
|
||||
After=network.target
|
||||
|
||||
[Service]
|
||||
Type=simple
|
||||
User=dank
|
||||
Group=dank
|
||||
WorkingDirectory=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native
|
||||
Environment="HOST=0.0.0.0"
|
||||
Environment="PORT=7770"
|
||||
Environment="SERVED_MODEL_NAME=frank-default-large"
|
||||
ExecStart=/home/dank/vllmScripts/scripts/serve-ling3-vllm.sh
|
||||
Environment="FRANK_LARGE_ENV_FILE=/home/dank/vllmScripts/scripts/frank-default-large.env"
|
||||
ExecStart=/home/dank/vllmScripts/scripts/serve-llama-frank-large.sh
|
||||
Restart=on-failure
|
||||
RestartSec=10
|
||||
|
||||
|
||||
Reference in new issue
Block a user