sgl-router: experimental Rust HTTP router for SGLang worker pools (#25851)

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Kangyan-Zhou
2026-05-25 15:34:05 +08:00
committed by GitHub
co-authored by Claude Opus 4.7
parent aae04b1241
commit 6e8fe176be
131 changed files with 28623 additions and 55 deletions
+20
View File
@@ -0,0 +1,20 @@
# sgl-router
Slim, KV-aware, OpenAI-compatible router for SGLang workers.
**Status:** functional single-worker HTTP proxy. Exposes `/v1/tokenize`,
`/v1/detokenize`, `/v1/models`, `/v1/chat/completions` (buffered and SSE),
plus `/healthz` / `/readyz`. Forwards to one configured worker via reqwest;
parity-tested against `transformers.AutoTokenizer`. Multi-worker routing,
service discovery, and observability still pending.
## Building
```bash
cd experimental/sgl-router
cargo build --release
```
## License
Apache-2.0.