There seems to be some incompatibility between TGI and Llama’s Function Calling, so you may need to use a slightly hacky workaround.
John6666
2
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Tool calling gets stuck in an infinite loop | 2 | 712 | April 12, 2025 | |
| Function calling not working with inference clients on (seemingly) any model | 10 | 1032 | February 8, 2025 | |
| Inference Endpoints - No working code examples | 3 | 232 | January 29, 2025 | |
| Endpoint issue with GPTQ | 0 | 238 | January 23, 2024 | |
| Unable to get inference results after deploying model to Inferende Endpoints | 0 | 31 | May 8, 2025 |