Repository navigation

fix(memory): send Qwen thinking controls through SGLang and vLLM chat templates - #348

Open

YaoleWu wants to merge 4 commits into

MemTensor:mainfrom

YaoleWu:codex/sglang-vllm-thinking-providers-v2

Open

fix(memory): send Qwen thinking controls through SGLang and vLLM chat templates#348
YaoleWu wants to merge 4 commits into
MemTensor:mainfrom
YaoleWu:codex/sglang-vllm-thinking-providers-v2

Commits on Sep 3, 2026
- fix(memory): add dedicated SGLang and vLLM thinking transports
  YaoleWu
  committed
  d4a5bc6
Commits on Oct 9, 2026
- Merge main into dedicated SGLang and vLLM thinking transports
  YaoleWu
  committed
  88275cb
Commits on Oct 14, 2026
- Merge upstream JSON fallback without losing dedicated thinking transports
  YaoleWu
  committed
  7e7726d
Commits on Oct 24, 2026
- Merge main and preserve dedicated thinking transports
  YaoleWu
  committed
  736cef1