Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions .github/workflows/publish-alpha.yml
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,8 @@ jobs:
node-version: 22
cache: pnpm
registry-url: https://registry.npmjs.org
- name: Install npm with trusted publishing support
run: npm install --global npm@latest
- name: Install dependencies
run: pnpm install --frozen-lockfile
- name: Verify alpha package
Expand Down
4 changes: 3 additions & 1 deletion CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,9 @@

## Unreleased

- No unreleased changes.
- Use QVAC CLI's `127.0.0.1:11434` endpoint as the CLI and documentation default.
- Add npm discovery keywords and a benefit-oriented package description.
- Clarify that this is an independent community project.

## 0.1.0-alpha.1 - 2026-07-10

Expand Down
13 changes: 8 additions & 5 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,9 @@
# qvac-bench

Public QVAC developer tooling from localhost41.
Command-line benchmarks for local QVAC OpenAI-compatible streaming endpoints.

> Independent community project maintained by localhost41. Not affiliated with
> or endorsed by Tether or QVAC.

## Local development

Expand Down Expand Up @@ -46,7 +49,7 @@ Benchmark a local QVAC OpenAI-compatible streaming endpoint:

```bash
qvac-bench \
--url http://localhost:8000/v1/chat/completions \
--url http://127.0.0.1:11434/v1/chat/completions \
--model qvac \
--prompt "Say hello in one short sentence." \
--max-tokens 64 \
Expand Down Expand Up @@ -182,7 +185,7 @@ pnpm build

# 3. Warm the endpoint once without recording the result.
node dist/cli.js \
--url http://localhost:8000/v1/chat/completions \
--url http://127.0.0.1:11434/v1/chat/completions \
--model qvac \
--prompt-name hello \
--max-tokens 64 \
Expand All @@ -192,7 +195,7 @@ node dist/cli.js \

# 4. Run the measured benchmark with the same inputs.
node dist/cli.js \
--url http://localhost:8000/v1/chat/completions \
--url http://127.0.0.1:11434/v1/chat/completions \
--model qvac \
--prompt-name hello \
--max-tokens 64 \
Expand Down Expand Up @@ -233,7 +236,7 @@ To reproduce a result:

```bash
node dist/cli.js \
--url http://localhost:8000/v1/chat/completions \
--url http://127.0.0.1:11434/v1/chat/completions \
--model qvac \
--prompt-name hello \
--max-tokens 64 \
Expand Down
11 changes: 10 additions & 1 deletion package.json
Original file line number Diff line number Diff line change
@@ -1,7 +1,16 @@
{
"name": "@localhost41/qvac-bench",
"version": "0.1.0-alpha.1",
"description": "QVAC developer tooling package: qvac-bench",
"description": "Benchmark local QVAC OpenAI-compatible streaming endpoints from the command line",
"keywords": [
"qvac",
"benchmark",
"cli",
"llm-benchmark",
"local-ai",
"openai-compatible",
"performance"
],
"license": "MIT",
"repository": {
"type": "git",
Expand Down
4 changes: 2 additions & 2 deletions src/cli.ts
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@ QVAC benchmark developer CLI.
Options:
-h, --help Show this help text
--url <url> QVAC OpenAI-compatible chat completions URL
Default: http://localhost:8000/v1/chat/completions
Default: http://127.0.0.1:11434/v1/chat/completions
--model <model> Model name to request. Default: qvac
--prompt <prompt> Prompt to send. Default: Say hello in one short sentence.
--prompt-name <name> Built-in prompt fixture to run: ${promptNames().join(", ")}
Expand Down Expand Up @@ -75,7 +75,7 @@ export interface BenchmarkDependencies {
}

const defaultOptions: BenchmarkOptions = {
url: "http://localhost:8000/v1/chat/completions",
url: "http://127.0.0.1:11434/v1/chat/completions",
model: "qvac",
prompt: "Say hello in one short sentence.",
maxTokens: 64,
Expand Down
2 changes: 1 addition & 1 deletion test/index.test.ts
Original file line number Diff line number Diff line change
Expand Up @@ -554,7 +554,7 @@ describe("qvac-bench", () => {

const result = await measureQvacLatency(
{
url: "http://localhost:8000/v1/chat/completions",
url: "http://127.0.0.1:11434/v1/chat/completions",
model: "qvac-local",
prompt: "hello",
maxTokens: 8,
Expand Down
Loading