Skip to content

Instantly share code, notes, and snippets.

View jlewi's full-sized avatar

Jeremy Lewi jlewi

View GitHub Profile
@jlewi
jlewi / Dockerfile
Created July 2, 2024 01:31
Triton Dockerfile
ARG TRITON_VERSION=2.46.0
ARG TRITON_CONTAINER_VERSION=24.05
ARG BASE_IMAGE=nvcr.io/nvidia/tritonserver:24.05-py3-min
############################################################################
## Production stage: Create container with just inference server executable
############################################################################
FROM ${BASE_IMAGE}
#!/usr/bin/env bash
#
# Build script for Triton Inference Server
#
# Exit script immediately if any command fails
set -e
########

File name: debug_gke_cpu_quota.md

Session: 01J04MJXC866JC17Z84Y698K20


▶️ Generated by Runme

Share your own terminal sessions, it's free and open source. Click here to learn more.

{
"$schema": "http://json-schema.org/draft-04/schema#",
"$ref": "#/definitions/Collection",
"definitions": {
"Collection": {
"properties": {
"items": {
"items": {
"$ref": "#/definitions/pilots.Tuple"
},
it('Written with DeploySentinel Recorder', () => {
// Load "https://github.com/jlewi/autobuilder-testing/issues/new"
cy.visit('https://github.com/jlewi/autobuilder-testing/issues/new');
// Resize window to 1920 x 859
cy.viewport(1920, 859);
// Fill "New test issue" on <input> #issue_title
cy.get('#issue_title').type("New test issue");
@jlewi
jlewi / gist:ceb4180b8d59124400985910d4253aee
Created May 13, 2023 00:20
_get_server_extension_metadata
def _get_server_extension_metadata(module):
"""Load server extension metadata from a module.
Returns a tuple of (
the package as loaded
a list of server extension specs: [
{
"module": "mockextension"
}
]
@jlewi
jlewi / gist:2e5897d28c7165e2f0299e03e065f0a9
Created March 23, 2023 00:18
example conversation with ChatGPT to write an sql query.
{
"title": "Is there a public bigquery dataset for GitHub?",
"creationTime": "2023-03-22T15:32:30.456",
"messages": [
{
"fromID": "0lShIJyQbEYatxFxW6jaicnzwDb2",
"toID": "1",
"blocks": [
{
"type": "text",
{
"title": "What is a changenotifier class in dart?",
"creationTime": "2023-03-20T15:46:07.385",
"messages": [
{
"fromID": "0lShIJyQbEYatxFxW6jaicnzwDb2",
"toID": "1",
"blocks": [
{
"type": "text",
<!DOCTYPE html>
<html>
<head>
<!--
If you are serving your web app in a path other than the root, change the
href value below to reflect the base path you are serving from.
The path provided below has to start and end with a slash "/" in order for
it to work correctly.
W0213 11:39:11.780602 66135 gcp.go:120] WARNING: the gcp auth plugin is deprecated in v1.22+, unavailable in v1.25+; use gcloud instead.
To learn more, consult https://cloud.google.com/blog/products/containers-kubernetes/kubectl-auth-changes-in-gke
apiVersion: apps/v1
kind: Deployment
metadata:
annotations:
autopilot.gke.io/resource-adjustment: '{"input":{"containers":[{"limits":{"cpu":"500m","ephemeral-storage":"1Gi","memory":"8Gi"},"requests":{"cpu":"250m","ephemeral-storage":"1Gi","memory":"1Gi"},"name":"server"}]},"output":{"containers":[{"limits":{"cpu":"250m","ephemeral-storage":"1Gi","memory":"1Gi"},"requests":{"cpu":"250m","ephemeral-storage":"1Gi","memory":"1Gi"},"name":"server"}]},"modified":true}'
deployment.kubernetes.io/revision: "11"
kubectl.kubernetes.io/last-applied-configuration: |
{"apiVersion":"apps/v1","kind":"Deployment","metadata":{"annotations":{},"labels":{"app":"service"},"name":"server","namespace":"chat"},"spec":{"replicas":1,"selector":{"matchLabels":{"app":"s