wmantly/turing-multi-gpu-llm-server
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Configure HauhauCS FastMTP 32K draft head, reasoning parameters, and non-thinking mode

Browse Source
This commit is contained in:
wmantly committed 2026-09-06 22:46:11 +00:00
1 parent 2af141b38e
commit cfeac35ad6
2 files changed
+22 -3
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

scripts/ollama-proxy.py
+4
View File
@@ -143,6 +143,10 @@ MODEL_TAGS = [
"Qwen3.8-27B-Uncensored",
"qwen3.8-27b:latest",
"qwen3.8-27b",
"qwen3.8-27b-aggressive-q3",
"qwen3.8-27b-aggressive-q3:latest",
"qwen3.8-27b-aggressive",
"qwen3.8-27b-aggressive:latest",
]
# Set to False to hide reasoning_content / thinking blocks entirely.