diff --git a/README.md b/README.md index 6ceff9a..118417d 100644 --- a/README.md +++ b/README.md @@ -15,7 +15,7 @@ param_nameparam_value The upstream parser (as of vLLM issue #32829) buffers string values until the closing tag arrives. For long strings (e.g., 4000+ characters of code), users see nothing until the entire value is complete — not true streaming. -## The Fix +## The Fix (Pulled from https://github.com/vllm-project/vllm/pull/39253) `glm4_moe_tool_parser.py` implements incremental string streaming: