Skip to main content

Integration testing, streaming utilities, and repetition detection for distributed LLM inference on DGX Spark clusters

Project description

mypy and pytests black-lint Cumulative Clones

dgxarley

Tooling for the DGX Arley K3s inference cluster — integration tests, streaming utilities, and CLI entry points for SGLang, Ollama, and OpenWebUI services.

Heureka! — Qwen3-235B-A22B MoE (AWQ 4-bit) running distributed inference across both DGX Sparks:

235B AWQ Heureka

sglang-raw — Dual-panel SSE stream viewer

sglang-raw: rendered response + raw JSON chunks

Dual-panel Rich TUI for inspecting SGLang's OpenAI-compatible streaming API in real time. The top half renders the AI response as it arrives, while the bottom half displays the raw JSON SSE stream chunks — showing fields like chat_completion_chunk, choices, delta, finish_reason, and model. Useful for debugging streaming behaviour, verifying token delivery, and understanding the wire format of the API.

sglang-raw — Think/text token classification

sglang-raw: token table with think/text classification

Token-level stream inspection with per-chunk breakdown in a structured table. Columns show the token type (think vs text), content, finish reason, and cumulative token count — visualizing how reasoning tokens (from <think>...</think> blocks) are separated from the actual output tokens. This view helps when tuning thinking budgets, verifying reasoning_parser behaviour, or diagnosing unexpected token classification.

What's included

CLI tools

Command Description
sglang-raw Interactive SSE stream viewer with dual-panel Rich display (interpreted output + raw JSON chunks)
sglang-test Direct SGLang client with sequential and parallel load testing (live Rich TUI)
openwebui-test OpenWebUI / LLM client with preset management and streaming
ollama-test Ollama API health, model, embedding, and chat completions tests
kceve-kvm RS232 serial control for KCEVE KVM1001A 10-port KVM switches (switch ports, query state, sniff)
kceve-kvm-web Web UI for KCEVE KVM control (FastAPI, requires dgxarley[web])
kceve-kvm-web-plain Lightweight web UI for KCEVE KVM control (stdlib http.server, no extra dependencies)

kceve-kvm-web — KCEVE KVM1001A Web UI

kceve-kvm-web: KVM switch control via browser

Browser-based control panel for the KCEVE KVM1001A 10-port KVM switch via RS232 serial. Shows the currently active input port on a virtual 7-segment display and allows switching between all 10 inputs with a single click. Commands are sent over a USB-to-RS232 adapter at 115200 baud using the X<channel>,1$ ASCII protocol.

Demo video

Remote test setup (serial over SSH tunnel)

If the KVM is connected to a remote host, you can tunnel the serial port via TCP:

# 1. On k3smaster (where the USB-RS232 adapter is connected): expose serial as TCP server
root@k3smaster ~ # socat tcp-listen:7000,reuseaddr,fork /dev/ttyACM0,b115200,raw,echo=0

# 2. On workstation: SSH tunnel to remote TCP port
user@workstation ~ $ ssh -N -L 7000:127.0.0.1:7000 root@k3smaster &

# 3. On workstation: create local PTY from TCP tunnel
user@workstation ~ $ socat pty,link=/tmp/kvm-serial,raw,echo=0 tcp:127.0.0.1:7000 &

# 4. On workstation: start web UI on the local PTY
user@workstation ~ $ kceve-kvm-web -d /tmp/kvm-serial -p 8080

Then open http://localhost:8080 in a browser.

Libraries

Module Description
dgxarley.integration.repetition_detector Offline n-gram, sentence, and loop repetition analysis for completed LLM outputs
dgxarley.integration.streaming_repetition_guard Real-time repetition detection for token streams with configurable thresholds

Installation

pip install dgxarley

Quick start

from dgxarley.integration.repetition_detector import detect_repetition

report = detect_repetition(llm_output)
print(report.summary())
# [LOW] score=0.12 — N-Gram 'this is a test' x2
from dgxarley.integration.streaming_repetition_guard import RepetitionGuard

guard = RepetitionGuard()
for chunk in llm_stream:
    token = chunk.choices[0].delta.content or ""
    result = guard.feed(token)
    if result.should_stop:
        print(f"STOP: {result.reason}")
        break

Requirements

  • Python >= 3.14

Source & documentation

Full documentation, network architecture, and Ansible playbooks: GitHub

License

This project is licensed under the LGPL where applicable/possible — see LICENSE.md. Some files/parts may use other licenses: MIT | GPL | LGPL. Always check per‑file headers/comments.

Authors

  • Repo owner (primary author)
  • Additional attributions are noted inline in code comments

Acknowledgments

  • Inspirations and snippets are referenced in code comments where appropriate.

⚠️ Note

This is a development/experimental project. For production use, review security settings, customize configurations, and test thoroughly in your environment. Provided "as is" without warranty of any kind, express or implied, including but not limited to the warranties of merchantability, fitness for a particular purpose and noninfringement. In no event shall the authors or copyright holders be liable for any claim, damages or other liability, whether in an action of contract, tort or otherwise, arising from, out of or in connection with the software or the use or other dealings in the software. Use at your own risk.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

dgxarley-0.0.33.tar.gz (71.9 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

dgxarley-0.0.33-py3-none-any.whl (81.5 kB view details)

Uploaded Python 3

File details

Details for the file dgxarley-0.0.33.tar.gz.

File metadata

  • Download URL: dgxarley-0.0.33.tar.gz
  • Upload date:
  • Size: 71.9 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: Hatch/1.16.5 cpython/3.14.3 HTTPX/0.28.1

File hashes

Hashes for dgxarley-0.0.33.tar.gz
Algorithm Hash digest
SHA256 2c7d51cde42454270cee13e05ad00d597dac3b7a13d0639cc09c0198edcabeae
MD5 b2c653f1c4ff6cab2a63a1c8fbdf4700
BLAKE2b-256 a838f1a769193befcc425485e1d38fb2c4667bdfd21d4ccaecb3b7ce931070f2

See more details on using hashes here.

File details

Details for the file dgxarley-0.0.33-py3-none-any.whl.

File metadata

  • Download URL: dgxarley-0.0.33-py3-none-any.whl
  • Upload date:
  • Size: 81.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: Hatch/1.16.5 cpython/3.14.3 HTTPX/0.28.1

File hashes

Hashes for dgxarley-0.0.33-py3-none-any.whl
Algorithm Hash digest
SHA256 ef28b3c169150f8a6ada7dabf8b3134111db0e5e3033d17a4ccbca8031babfc7
MD5 4348397d6e2ac0cf86d7155e717cefe3
BLAKE2b-256 01cb373bba659f0d0454e214f30d9a79692b2125fb2ff68bff7f4df96504fe00

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page