Inital commit

This commit is contained in:
2026-06-04 18:11:26 -05:00
commit 9bd7f5838e
24 changed files with 2454 additions and 0 deletions
+31
View File
@@ -0,0 +1,31 @@
# TrueCluster
Prototype heterogeneous pipeline-parallel LLM inference cluster.
See [`SPEC.md`](SPEC.md).
## Install
```bash
pip install -e .
```
## Run a cluster
```bash
truecluster cluster --model Qwen/Qwen2.5-0.5B-Instruct --max-nodes 1 --quant fp16
```
## Run a node
```bash
truecluster node --cluster-host 127.0.0.1 --cluster-port 7001 --device auto
```
## Generate
```bash
curl http://127.0.0.1:8000/v1/completions \
-H 'content-type: application/json' \
-d '{"model":"Qwen/Qwen2.5-0.5B-Instruct","prompt":"Hello","max_tokens":32}'
```