-
## Description of Issue
Loading render distances Higher than 32 Chunks (Tested specifically 48 and 64 chunks), causes the game crash with error code -1073740791 or -1073741819.
PC Specs in case…
-
Hi,
I noticed that you trained the NLP emulator with the first 30 chunks of Pile dataset. I wonder how large are the 30 chunks? Or in other words, how many chunks does Pile have? The original Pile …
-
In looking at parallelism, @cindytsai identified a trend for AMR datasets that the graph is roughly flat. This seems to be because of `_identify_base_chunk`, which is a rather large and all-consuming…
-
Rendering performance can sometimes be slow, with re-renders occurring whenever the app context changes in all components that depend on it.
This is particularly notable when changing field values,…
-
I'm benchmarking vicuna 13B using trt-llm v0.9.0 on 2*A30 GPU, and try the following configurations.
![image](https://github.com/NVIDIA/TensorRT-LLM/assets/26128514/49016591-0305-4842-a902-80f667d9…
-
### What is your issue?
_I think that this is a longstanding problem. Sorry if I missed an existing github issue._
I was looking at an Dask-array-backed Xarray workload with @phofl and we were bo…
-
### What Roadmap is this project for?
Backend roadmap
### Project Difficulty
Intermediate
### Add Project Details
You are required to build a streaming server using Node.js and TypeScript that ca…
-
### 🚀 The feature, motivation and pitch
This has introduced chunks:
https://github.com/pytorch/pytorch/pull/141592
Here native upstream for CCCL 2.8:
https://github.com/NVIDIA/cccl/pull/2400#i…
-
### Describe the documentation issue
Some models have a "batch dimension" in their inputs suggesting that entries along that dimension are independent of each other. Models of this kind are good cand…
-
The C++ af-dist implementation added in #157 (and notes in #160) is surprisingly slow. In some informal tests it looks like it's about 3X slower than Python Zarr, just retrieving the chunks. There's …