4 Commits

Author	SHA1	Message	Date
Parth Sareen	cc90a035a0	model/parsers: add stable tool call indexing for glm47 and qwen3 parsers (#14484)	2026-02-26 18:14:29 -08:00
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
Jeffrey Morgan	da70c3222e	model: support for qwen3.5 architecture (#14378)	2026-02-24 20:08:05 -08:00
Patrick Devine	9aefd2dfee	model: add qwen3 support to mlxrunner (#14293)	2026-02-17 13:58:49 -08:00