Mustafa Ali

Unable to run benchmark of mixtral

2

Hi, I am trying to benchmark Mixtral-7B,, however I get this error: ``` BS: 64, ISL/OSL: 128,128 ^A[TensorRT-LLM][ERROR] 3: [executionContext.cpp::setInputShape::2309] Error Code 3: API Usage Error (Parameter check failed at:...

Need to enable DHCP server for AP mode to assign ip addresses for clients

1

Hello, I need to enable DHCP when the module is in AP mode so that any client connected to it can get automatic ip, in stock firmware, AT+CWDHCP command could...

can't run train.py

4

I ran `ipython3 train.py ` I got this:  I installed sonnet from this command `$ pip install dm-sonnet`

use tensor cores

2

Great repo! I learned a lot from it and the blog, thank you! I was wondering if there is an easy way to rewrite the kernels to use tensor cores...

Are you planning on supporting Flash decoding with H100 specific instructions? I mean FA3 for decoding?

[FEA] FP8 Convolution

3

**Is your feature request related to a problem? Please describe.** I was wondering if CUTLASS is planning to support FP8 inputs of Conv kernels (output can be FP16 or FP32)...

Hi I tried running a sdpa_fp8 graph where seqlen_q and seqlen_k are different, however it seems that it only uses the seqlen_q as in performance is the same when I...