Skip to content

FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.

test(server): list the llama and qwen2 gguf archs in the parser auto-selection tables (#727)

Xiaoze Fan312f324d65b3
diff --git a/tests/server/test_parser_auto_selection.py b/tests/server/test_parser_auto_selection.py
index e1eb8798..6bdc6579 100644
--- a/tests/server/test_parser_auto_selection.py
+++ b/tests/server/test_parser_auto_selection.py
@@ -31,14 +31,16 @@ ANON_PATH = "/models/anon"
# parser, and a new architecture landing here is the bug this file exists to catch.
NO_REASONING_FORMAT = {
"LlamaForCausalLM",
+ "LlamaGGUFForCausalLM",
"MistralForCausalLM",
"Mistral3ForConditionalGeneration",
"Qwen2ForCausalLM",
+ "Qwen2GGUFForCausalLM",
}
# `llama3` is the end of the cascade -- the answer when nothing matched.
GENERIC_TOOL_CALL_FALLBACK = "llama3"
-NO_DEDICATED_TOOL_FORMAT = {"LlamaForCausalLM"}
+NO_DEDICATED_TOOL_FORMAT = {"LlamaForCausalLM", "LlamaGGUFForCausalLM"}
class _Config: