oleotiger

Is hybrid call stack supported?

1

**Is your feature request related to a problem? Please describe.** I want to catch the call stack from pytorch to C++ backend. For example, which function is called in C++...

[Inference Performance of LLAMA-2 posted by Nvidia 1](https://docs.nvidia.com/nemo-framework/user-guide/latest/performance/llama.html) According to the link above, the inference lantecy of LLAMA-2-13B with A100 80GB SXM4 at batch size=1 and tp=1, is less than...

GEMM API for efficient LLM inference with W8A16

3

I want to perform inference on quantized LLAMA (W8A16) on ARM-v9 (with SVE) using oneDNN. The LLAMA weights are per-group quantized. Based on my understanding, I need to prepack the...

硬件配置最小要求？

5

readme中要求最少是8张A100，但是我没有如此多的A100,分布式也不够，所以想问一下： 1、 2张A100能跑起来吗？哪怕速率慢一些，只是要求能够run，能通过简单修改在两个A100跑起来 2、如果是纯CPU运行，可以out-of-box运行吗？需要做哪些修改？

`Use of JDK7 is required.` Why must compile with JDK7? JDK7 is not compatible with `numactl`. I want to bind the client on a numa node with `numactl`. Java JDK11...

What is the max data size which can be processed by netdata-timescale-relay?

3

Here is my problem. When I export metrics from metrics at every 1s (as collected) from parent node and there is one child node, I get error from netdata like...