Jeffrey Morgan d98dda4676 model: fix qwen3 tool calling in thinking (#14477) ...

Align Qwen parser behavior with Transformers serve by allowing <tool_call> parsing while still in thinking collection.

Changes:

- qwen3vl: detect <tool_call> before </think> in thinking state and transition to tool parsing

- qwen3: same thinking-state tool detection and partial-tag overlap handling

- tests: update qwen3vl thinking/tool interleaving expectations

- tests: add qwen3 cases for tool call before </think> and split <tool_call> streaming

2026-02-26 16:13:18 -08:00

..

imageproc

deepseekocr

2025-11-18 16:11:37 -08:00

input

batch: use tensors for outputs (#12185)

2025-09-15 14:33:06 -07:00

models

model: add support for qwen3.5-27b model (#14415)

2026-02-25 01:09:58 -08:00

parsers

model: fix qwen3 tool calling in thinking (#14477)

2026-02-26 16:13:18 -08:00

renderers

model: support for qwen3.5 architecture (#14378)

2026-02-24 20:08:05 -08:00

model_test.go

models: add nemotronh architecture support (#14356)

2026-02-22 15:09:14 -08:00

model.go

move tokenizers to separate package (#13825)

2026-02-05 17:44:11 -08:00