Lumpiasty/klaster
0
0
Fork 0
Code Issues Pull Requests 2 Packages Projects Releases Wiki Activity

add llama-swap optimizations recommended by claude
ci/woodpecker/push/flux-reconcile-source Pipeline was successful
Details

Browse Source
This commit is contained in:
Lumpiasty
2026-05-31 04:49:11 +02:00
parent 353155f7ad
commit 7e51eb8159
1 changed files with 5 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
apps/llama/configs/config.yaml
+5 -6
View File
@@ -4,16 +4,16 @@ logToStdout: "both" # proxy and upstream
macros:
base_args: "--no-warmup --port ${PORT} --mlock --no-mmap"
common_args: "--fit-target 1536 --no-warmup --port ${PORT} --no-mmap"
common_args: "--fit-target 256 --no-warmup --port ${PORT} --no-mmap -tb 12 -t 6"
cpu_args: "--no-warmup --port ${PORT} -ngl 0"
ctx_64k: "--ctx-size 65536"
ctx_128k: "--ctx-size 131072"
ctx_256k: "--ctx-size 262144"
qwen35_think_args: "--temp 1.0 --top-p 0.95 --top-k 20 --min-p 0.00 -ctk q4_0 -ctv q4_0 --presence_penalty 1.5 --reasoning on"
qwen35_nothink_args: "--temp 0.7 --top-p 0.80 --top-k 20 --min-p 0.00 -ctk q4_0 -ctv q4_0 --presence_penalty 1.5 --reasoning off"
ctx_256k: "--ctx-size 131072"
qwen35_think_args: "--temp 1.0 --top-p 0.95 --top-k 20 --min-p 0.00 --presence_penalty 1.5 --reasoning on"
qwen35_nothink_args: "--temp 0.7 --top-p 0.80 --top-k 20 --min-p 0.00 --presence_penalty 1.5 --reasoning off"
qwen35_35b_heretic_mmproj: "--mmproj-url https://huggingface.co/unsloth/Qwen3.5-35B-A3B-GGUF/resolve/main/mmproj-F16.gguf --mmproj /root/.cache/llama.cpp/unsloth_Qwen3.5-35B-A3B-GGUF_mmproj-F16.gguf"
qwen35_4b_heretic_mmproj: "--mmproj-url https://huggingface.co/unsloth/Qwen3.5-4B-GGUF/resolve/main/mmproj-F16.gguf --mmproj /root/.cache/llama.cpp/unsloth_Qwen3.5-4B-GGUF_mmproj-F16.gguf"
gemma4_sampling: "--temp 1.0 --top-p 0.95 --top-k 64 -ctk q4_0 -ctv q4_0"
gemma4_sampling: "--temp 1.0 --top-p 0.95 --top-k 64"
hooks:
on_startup:
@@ -70,7 +70,6 @@ models:
--top-p 0.95
--top-k 40
--repeat-penalty 1.0
-ctk q4_0 -ctv q4_0
${common_args}
"Qwen3.5-35B-A3B-GGUF:Q4_K_M":