-
**Single shard is bottleneck while broadcast join table to all shard and join table is big, broadcast join table cost too much time**
**in spark, torrent broadcast mechanism can used to fix single…
-
@gbaraldi requested a writeup of the design I had for vectorized primitives.
I have no particular plans to implement this myself anytime soon, so this is
up for grabs.
# Background
A longstanding (…
-
Hi, I'm working on the attention mechanism for face recognition models, I'm using the ir model as a backbone, but I don't know much about the details of the implementation of grad-cam, what exactly sh…
-
----
## 🚀 Feature
I would like to propose adding a feature to LitServe that enables models to be deployed with a keep-alive functionality, similar to what Ollama provides. This feature would…
-
## Overview
Some models implement a denormalized field (ie. `_count`) to store the count value for a related model in the project. Currently, no tracking mechanism (increment or decrement) is impleme…
-
### Details
Solution:
Metric: Primary: Performance metrics (e.g., execution time, memory usage, throughput). Secondary: Code quality score, resource utilization metrics.
Search Space:
Algorithm o…
-
The idea is perhaps future-looking, but I'd like to bring it up for discussion.
## Motivations
* Reduce the GPU/NPU memory required for completing a use case (e.g. text2image).
* Reduce the mem…
-
The model is noticeably slower (compared to version pre-1.0). Need to do
1. profiling to identify the bottlenecks and see how they can be eliminated.
1. Is it worth considering parallelization?
Known…
-
**Is your feature request related to a problem? Please describe.**
The problem is that the management component lacks high availability (HA) support. Currently, the management component is central to…
JaSei updated
1 month ago
-
**Title : Email Generator**
**Issue Summary:**
- The provided Java source files are part of an Email Generator application. The application appears to generate and handle emails programmatically…