-
In discussions about the first version of the Platforms whitepaper, TAG Sustainability brought up that a platform could offer a capability to optimize workloads for sustainability and efficiency, see …
-
### Comment:
A conda-forge environment with nothing but pytorch for cuda in it currently ways in at 7.2GB, which is perceived to be rather on the heavy side of things.
Looking at potential for slimm…
-
This is a follow-up from https://github.com/dotnet/source-build/issues/4005
# 🚧 THIS IS A WORK IN PROGRESS RIGHT NOW 🚧
## Document .NET's behaviour running on FIPS-enabled systems
Issue: https:/…
-
#### Why is this needed?
Kubernetes is widely adopted for its ability to manage containerized workloads efficiently. However, determining the appropriate resource specifications (CPU and memory) fo…
caohe updated
11 months ago
-
I believe @Tryneus and @brendoncarroll have the most context, but IIUC if a job with an additive workload runs, it may merge its output into its parent commit's hashtree. This works for the job's outp…
-
Hi!
Did anyone try before applying Profile-Guided Optimization (PGO) on Ruffle? I can expect that this optimization can reduce CPU usage for the project (since it [helps](https://github.com/zamazan…
-
```
# rg "limit executor close takes a long time" tidb.log
12789:[2024/04/19 19:10:22.385 +08:00] [INFO] [executor.go:1424] ["limit executor close takes a long time"] [elapsed=2.107365ms]
12791:[20…
-
Need to instrument the compiler on specific workloads (feed forward, qubo, pilotnet) and present analysis
### Conditions of satisfaction
- Instrument Feed Forward Network spanning across 1 chip, 2 ch…
-
On some systems there are scenarios where we know we can perform a rechunk entirely in-memory without writing to disk. For example if I locally run this test which performs a single rechunk stage:
…
-
Hi!
Recently I checked Profile-Guided Optimization (PGO) improvements on multiple projects. The results are [here](https://github.com/zamazan4ik/awesome-pgo/). Since PGO shows improvements for many…