Repository Issue Activity (beta)

#157 Verify evals on Papers with Code

#137 Ascend_NPU README 中 PYTHON_LIB_PATH 环境变量指向错误路径

#154 [论文分享] LUMEN：用电子能量"旋钮"制造自然界没有的光 —— 13.5nm EUV 光源的闭式全量验证（附 2 篇论文 PDF）

#152 Feature Request: Agent 子智能体支持 model 参数（Pro-Flash 双模型协作降低 token 成本）

#151 Open Clow_Putri

#102 Support OpenAI's Codex CLI

#142 使用vLLM部署 GLM-4.7-Flash 模型输出思考标签<think>异常

#138 Priorità Assoluta: Failure in Real-Time Temporal Grounding (Data/Anno Errata)

#135 GLM-4.6回复乱码

#145 📋 Documentation Enhancement Suggestion

#146 GLM-4.7 流式输出下 工具调用参数不完整

#147 vllm-ascend 启动GLM-4.5 FP8后，请求的输出结果乱码

#140 Bug: Webfrontend - Clone Chat.

#143 glm-4.7-flash sometimes inserts Chinese characters in generated C code in an English language Claude session

#144 如何使用V100部署glm4.7

#131 GLM4.7-30B推理速度问题，并且倾向于输出很长的回答

#133 SLOW!

#139 请问GLM-4.7使用gpqa数据集evaluate时使用了怎样的提示词？

#134 vllm/transformer cannot load GLM-4.7-flash due to module name mismatch

#71 UI fix while editing the question

#63 vLLM offline batch inference for video understanding example

#100 GLM 4.6 API Missing Reasoning Traces

#94 RuntimeError when deploying GLM-4.5-Air-FP8 by vLLM in 8*RTX3090

#132 使用A100启动的时候报这个错误，如何解决？

#112 Always reporting "The following fields were present in the request but ignored: {'reasoning'}" when using claude code with claude-code-router