Inferlab Integration for SGLang
Framework-specific planning and rendering for running SGLang servers through Inferlab. The consuming workspace supplies SGLang and its hardware runtime; this package supplies only the Inferlab integration boundary.
See the Inferlab repository for workspace authoring and supported topology documentation.
When profiling intent is enabled, the integration declares every single,
prefill, and decode model-serving replica as a capture target of the
effective mechanism. Managed collection opens the Nsight Systems range
through POST /start_profile with SGLang's CUDA_PROFILER activity and
closes it through POST /stop_profile; engine trace renders the
control-plane-assigned trace directory into SGLANG_TORCH_PROFILER_DIR and
controls the window through the same action pair with the GPU activity.
InferLab, not this package, owns the profiler lifecycle, capture plan, report
verification, cleanup, and records.
For direct single, setting enable_metrics = true enables SGLang's native
Prometheus endpoint and declares /metrics to InferLab. Without that effective
setting the integration advertises no server-metrics capability.
1 maintainer
Metadata
1 maintainer
Release files for inferlab-integration-sglang 0.12.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| inferlab_integration_sglang-0.12.1-py3-none-any.whl | Python 3 | none | any | Details |
Release files / inferlab_integration_sglang-0.12.1-py3-none-any.whl
| Download URL | inferlab_integration_sglang-0.12.1-py3-none-any.whl |
|---|---|
| Size | 16.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
51f57dbae2ddf5a986d0fabe8294753ba34b1c509504144553ce1942ba464f17
|
|
BLAKE2b-256 checksum How to use checksums |
ff210a35c8541b7a74e27122270b1e418e1d93c07e643c3bcd3f74bb5ea89f4a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.14.7
|
