Yuanpeng Li

MicroCause疑问

2

很棒的工作！不过有两个疑问： 1. MicroCause的实现，并没有按照文章里的partial correlation的方式计算Q 2. 想问下您提到的DyCause是哪篇文章呢？是暂时还在投稿吗？ 期待您的解答

[Bug]: When starting deepseek-coder-v2-lite-instruct with vllm on 4 GPUs, one of them is at 0%.

6

### Your current environment ```text Collecting environment information... PyTorch version: 2.3.0+cu121 Is debug build: False CUDA used to build PyTorch: 12.1 ROCM used to build PyTorch: N/A OS: Debian GNU/Linux...

[Bug]: deepseek-coder-v2-lite-instruct; Exception in worker VllmWorkerProcess while processing method initialize_cache: [Errno 2] No such file or directory: '/root/.triton/cache/de758c429c9ff1f18930bbd9c3004506/fused_moe_kernel.json.tmp.pid_1528_587007', Traceback (most recent call last):

6

### Your current environment ```text Collecting environment information... PyTorch version: 2.3.0+cu121 Is debug build: False CUDA used to build PyTorch: 12.1 ROCM used to build PyTorch: N/A OS: Debian GNU/Linux...

[Feature]: deepseek-v2 awq support

3

### 🚀 The feature, motivation and pitch Is the deepseek-v2 AWQ version supported now? When I run it, I get the following error: ``` [rank0]: File "/usr/local/lib/python3.9/dist-packages/vllm/model_executor/models/deepseek_v2.py", line 135, in...

### Your current environment ```text PyTorch version: 2.4.0+cu124 Is debug build: False CUDA used to build PyTorch: 12.4 ROCM used to build PyTorch: N/A OS: Debian GNU/Linux 11 (bullseye) (x86_64)...

### Your current environment ```text The output of `python collect_env.py` ``` ### How would you like to use vllm I deployed the fp8 quantized model of deepseek-v2.5 using vllm and...

Is there any plan to support deepseek-v2?

[Bug]DeepSeek-R1 IndexError: index 2383 is out of bounds for dimension 0 with size 2383

2

### 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. -...