-
### Motivation.
At a high level, we at Neural Magic are writing a custom compiler for Torch Dynamo to define a system within vLLM where we can write graph transformations. The main goal is a separa…
-
Came across this when working on https://github.com/dask/distributed/pull/4347 . The new annotations machinery is attached to high level graph `Layer`s. However, in the optimization step, layers can b…
-
Hi!
I'm a high energy particle physicist using dask, [dask-awkward](https://github.com/dask-contrib/dask-awkward), and [dask-histogram](https://github.com/dask-contrib/dask-histogram) to compute co…
-
-
我们图上的组合优化问题，例如 Graph maxcut，下面的论文提出了对图结构进行了编码的方案：
- 论文 Learning Combinatorial Optimization Algorithms over Graphs （宋乐教授）
- 代码 https://github.com/Hanjun-Dai/graphnn
直接复现上面的代码，因为版本问题，不容易，我有以下建议：
-…
-
Thank you for this excellent implementation. I'd like to suggest an optimization that could significantly speed up inference and enable streaming output.
Currently, there are two GPT2 graphs:
1.…
-
### Issue Type
Bug
### Source
pip (mct-nightly)
### MCT Version
PR #1186
### OS Platform and Distribution
Linux Ubuntu 22.04
### Python version
3.10
### Describe the issu…
-
[Bayesian optimisation of functions on graphs](https://proceedings.neurips.cc/paper_files/paper/2023/hash/86419aba4e5eafd2b1009a2e3c540bb0-Abstract-Conference.html)
```bib
@article{wan2023bayesian,
…
-
Hello. I am reaching out to seek clarification on two aspects mentioned in the paper associated with your repository:
1. The paper discusses the iterative optimization of prompts using AST, CFG, an…
-
Is there a way reset a graph back to its original state (information, estimates etc) after optimizing it once. I wish to optimize the graph multiple times with different initial priors so I want to re…