zhjunqin

Sort input/output in PreProcessPrediction

4

In direct_session.cc https://github.com/tensorflow/tensorflow/blob/master/tensorflow/core/common_runtime/direct_session.cc#L1514, it always emplaces key to executors_, then a lot of keys are added to map, which leads to a lot of memory usage. If 10 input tensors,...

## 🐛 Bug mlc_ai_nightly_cu121-0.15.dev315-cp310-cp310-manylinux_2_28_x86_64.whl mlc_llm_nightly_cu121-0.1.dev1166-cp310-cp310-manylinux_2_28_x86_64.whl benchmark with llama3 model, got following error: INFO: 127.0.0.1:57104 - "POST /v1/chat/completions HTTP/1.1" 200 OK Exception in thread Thread-1 (_background_loop): Traceback (most recent call last):...

playground支持书生·浦语集成至LangChain 制作OpenMMLab浦语知识库

请问，商用的请求已经过去了 7 个工作日，还是没有收到回复的消息

1

### 是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this? - [X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions ### 该问题是否在FAQ中有解答？ | Is there an...

商用的授权应该是授权给公司的主体，不应该是个人的主体

1

### 是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this? - [X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions ### 该问题是否在FAQ中有解答？ | Is there an...

能详细展开说一下提出的 “LLM x MapReduce” 么

1

### Feature request / 功能建议 请问提到 原生支持 32k 上下文长度，32k 长度内大海捞针全绿。提出 LLM x MapReduce ，理论可处理的上下文长度达到 +∞ 能详细展开说一下提出的 “LLM x MapReduce” 么？

[Bug] MiniCPMV-2.6 HF 的推理结果和 lmdeploy 结果不一致

7

### Checklist - [X] 1. I have searched related issues but cannot get the expected help. - [X] 2. The bug has not been fixed in the latest version. -...

Add support for arm64 platform

7

**Is your feature request related to a problem? Please describe.** A clear and concise description of what the problem is. Ex. I'm always frustrated when [...] **Add support for arm64...