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 10, 22:45 UTC
[Doc] Add tool call parser documentation for GPT-OSS models (#31212)
Signed-off-by: Amith KK <amithkumaran@gmail.com>
Amith KK committed
Dec 25, 2025 at 10:59 UTC
42826bbccd04d71d88e19f51a0d0b3d98f29d780
1 file changed
+9
docs/features/tool_calling.md
+9
@@ -317,6 +317,15 @@ Supported models:
317
318
Flags: `--tool-call-parser deepseek_v31 --chat-template {see_above}`
319
320
+### OpenAI OSS Models ('openai`)
321
+
322
+Supported models:
323
+
324
+* `openai/gpt-oss-20b`
325
+* `openai/gpt-oss-120b`
326
+
327
+Flags: `--tool-call-parser openai`
328
+
329
### Kimi-K2 Models (`kimi_k2`)
330
331
Supported models: