JaheimLee

Results 59 comments of JaheimLee

下载模型的时候提示 HTTPSConnectionPool(host='cdn-lfs-us-1.hf-mirror.com', port=443): Read timed out.

我也一样，最近网络非常不稳定，即使连接上也只有几百K

[V1][Frontend] Improve Shutdown And Logs

I encountered a timeout error when using torch compile. Why use `timeout: Optional[float] = 180.0`?

[Core/Bugfix] Add FP8 K/V Scale and dtype conversion for prefix/prefill Triton Kernel

Can not work on NVIDIA Ampere GPU, for example 3090.

[Core/Bugfix] Add FP8 K/V Scale and dtype conversion for prefix/prefill Triton Kernel

> > Can not work on NVIDIA Ampere GPU, for example 3090. > > Unfortunate limit of Triton Does [#5975](https://github.com/vllm-project/vllm/pull/5975) help for this?

bert-base-uncased和bert-base-chinese拉不了。

今天经常有timeout问题

[Experimental Feature] Huggingface model training

Hi! Any updates?

unable to run vllm model deployment

Same issue. And vllm 0.5.1 works well.

[V1] [Spec Decode] Support random sampling for spec decode

Hi, I always got the following error when my server ran for a long time (a whole night). ``` ERROR 03-16 09:11:23 [core.py:337] EngineCore hit an exception: Traceback (most recent...

Enable FlashInfer V1 FP8 kv cache

I installed `flashinfer-python==0.2.5` from pypi and got no error. But the output is nonsense. BTW, my GPU is 3090. ``` 矍annisitrustvolt Ngo(ListNodeSENT jes mysqli炆 powerhouseสามารสามารПодроб@GeneratedValueПодробПодроб琇สามารПодробПодробสามารأوضПодробПодробannisॐ Dexter矍与时俱ALARПодробПодроб就够annisПодробПодробПодробПодробПодробПодробПодроб ```