-
**Describe the bug**
I tried running deepspeed zero 3 on a new huggingface model and got the following error:
[2023-12-13 04:12:18,837] [WARNING] [parameter_offload.py:86:_apply_to_tenso…
-
### Describe the bug
error:
```bash
Uncaught Svelte error: state_unsafe_mutation
Updating state inside a derived or a template expression is forbidden. If the value should not be reactive, declare…
-
### 🐛 Describe the bug
Hi Dears:
I found out that if I use torch==1.14, it'll turn out some error during import:
```
colossalai check
Traceback (most recent call last):
File "/home/mcc311nyc…
-
Hi there,
i am trying to run a unit test that i wrote to test a certain functionality.
It works fine if let it execute through "sudo docker build -t moe_container ."
However i would like to be abl…
-
requirements.txt中是torch 2.0.0；安装的时候和triton 2.1.0 不兼容；
安装时triton改为2.0.0安装；
安装后单独更新安装triton至2.1.0版本；
server可以正常运行，请求时发生错误：
> /root/.triton/llvm/llvm+mlir-17.0.0-x86_64-linux-gnu-centos-7-rel…
-
Hi,
I like your app and I was wondering if we could add search engine as "mods" or something like that.
And can we add search engine now easily? (I don't know kotlin well)
Thanks for this app
-
The vLLM [fused moe kernel](https://github.com/vllm-project/vllm/blob/main/vllm/model_executor/layers/fused_moe.py) used for Mixtral uses the standard data parallel parallelization which works well wi…
-
## 🐛 Bug
## To Reproduce
Steps to reproduce the behavior:
(mlc-chat-venv) hhg@dell:~/mlc-llm$ mlc_llm convert_weight ./dist/models/music-4-rwkv-converted/ --quantization q4f16_1 --source-…
-
### Your current environment
```text
The output of `python collect_env.py`
```
### 🐛 Describe the bug
We received quite a lot report about "Watchdog caught collective operation timeout", which …
-
motan 有没有已开发的监控平台，麻烦看到的大牛们介绍一下，谢谢啦