A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 16:00 UTC
[Frontend] Fix typo in tool chat templates for llama3.2 and toolace (#14501)
Signed-off-by: Ben Jackson <ben@ben.com>
Ben Jackson committed
Apr 6, 2025 at 00:44 UTC
eb07c8cb5b72f08291886ffa4d5d7b19af59c7a2
2 files changed
+2
-2
examples/tool_chat_template_llama3.2_pythonic.jinja
+1
-1
@@ -76,7 +76,7 @@
76
{{- tool_call.name + '(' -}}
77
{%- for param in tool_call.arguments %}
78
{{- param + '=' -}}
79
- {{- "%sr" | format(tool_call.arguments[param]) -}}
79
+ {{- "%s" | format(tool_call.arguments[param]) -}}
80
{% if not loop.last %}, {% endif %}
81
{%- endfor %}
82
{{- ')' -}}
examples/tool_chat_template_toolace.jinja
+1
-1
@@ -44,7 +44,7 @@
44
{{- tool_call.name + '(' -}}
45
{%- for param in tool_call.arguments %}
46
{{- param + '=' -}}
47
- {{- "%sr" | format(tool_call.arguments[param]) -}}
47
+ {{- "%s" | format(tool_call.arguments[param]) -}}
48
{% if not loop.last %}, {% endif %}
49
{%- endfor %}
50
{{- ')' -}}