Michael Act
Michael Act
## Premise As I see, this python script hasn't updated for 3 years, and maybe some newest python version, have bug while running it. I had this too, somehow an...
Hi, `Crizstian/cinema-microservice` maintainers. This pull request is made only to show how the `cinema-microservice` application deployment on top of Kubernetes. Also my practical lessons about Kubernetes. You may not want...
### Description In `dmesg -T` or linux diagnostic messages, it indicates that the container was shut down due to running out of memory. ``` [Tue Feb 20 19:15:36 2024] oom-kill:constraint=CONSTRAINT_NONE,nodemask=(null),cpuset=/,mems_allowed=0,global_oom,task_memcg=/docker/e9d912458f1530f0d9f586ab3bdca1015f45cbb5cd59cddde...
Previously, I struggled to create a build filter with enumeration of steps. This may be helpful for others in the future who want to create complex filter queries, like myself.
Changes: > The operation to power off (stop) a virtual machine. The virtual machine can be restarted with the same provisioned resources. **You are still charged for this virtual machine.**
https://zlib.net/pigz/
Example configuration: ``` spec: notification: delivery: subject: '{{ if eq .Build.Status 3 }}✅ Build Successful ({{ .Build.Substitutions.REPO_NAME }}){{ else }}❌ Build Failure ({{ .Build.Substitutions.REPO_NAME }}){{ end }} | {{.Build.Substitutions._COMMIT_MESSAGE}}' ```
### System Info I'm using `ghcr.io/huggingface/text-generation-inference:3.0.1` container image. ## Issue Description Hi everyone! I'm using the `Qwen/Qwen2.5-14B-Instruct-GPTQ-Int8` LLM model for benchmarking with multiple concurrent requests. However, when I send 10...
### Contact Details _No response_ ### What happened? I can't use the `--lora` parameter. I expected it to work, but maybe I’m specifying the parameters wrong. Has anyone experienced this...