smelt
This-host GPU efficiency profiler for vLLM. One model, one server.
Objective: minimize $/1M tokens subject to your p95 latency SLO.
You already know the GPU-hour price. Smelt turns a live nvidia-smi +
vLLM /metrics sample into $/hour → tok/s → $/1M tokens, names waste
it can measure, and tells you whether the last flag change won.
pip install smelt-gpu && smelt analyze --demo --gpu-hourly 3.89
make run # this repo: install from PyPI + scan/analyze/optimize
make install # editable checkout + dashboard
smelt scan --vllm-url http://127.0.0.1:8000
smelt analyze --gpu-hourly 3.89
smelt experiment save --name before
# change one vLLM flag, reload
smelt experiment compare --baseline before --slo-ms 500
make dev # API :8741 + dashboard :3010
PyPI name is smelt-gpu; the CLI stays smelt. smelt --version is the version.
Smelt does not restart vLLM or edit its flags. You apply the change;
it records and compares. Keep the candidate only if $/1M dropped (or
same cost, more tok/s) and p95 still meets the SLO.
If nothing is live, analyze falls back to a sample fleet
(96×H100 + 32×H200). --demo forces that.
The wheel is the CLI + smelt serve. The Next.js dashboard is this repo
only (make dev). Full notes: docs/.
Use it next to your vLLM
pip install smelt-gpu
smelt analyze --vllm-url http://127.0.0.1:8000 --gpu-hourly 3.89
In Python:
from smelt.integrations.scan import collect_host
from smelt.snapshot import fleet_from_snapshot, host_summary
snap = collect_host(vllm_url="http://127.0.0.1:8000")
fleet = fleet_from_snapshot(snap, gpu_hourly=3.89)
print(host_summary(fleet))
Or smelt serve and GET /api/fleet?live=true. How to wire this into a
job or another service: docs/use.md.
Improve it
make install && make hooks
make test
make test-live # this GPU + a server
make verify
New GPU prices → classify_gpu / GPU_HOURLY_USD. New /metrics
fields → smelt/integrations/vllm.py plus a fixture under
tests/fixtures/. Waste rules → _opportunities() in snapshot.py.
Details: docs/use.md.
Metadata
Release files for smelt-gpu 0.2.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| smelt_gpu-0.2.2.tar.gz | 34.3 kB | Without provenance | Details for smelt_gpu-0.2.2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| smelt_gpu-0.2.2-py3-none-any.whl | Python 3 | none | any | Details for smelt_gpu-0.2.2-py3-none-any.whl |
Total release size: 61.2 kB
Release files / smelt_gpu-0.2.2.tar.gz
| Download URL | smelt_gpu-0.2.2.tar.gz |
|---|---|
| Size | 34.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
6d27ce4a16545db33d483c37494b2a244bad452b366f9490431a0cf7d1f5807c
|
|
BLAKE2b-256 checksum How to use checksums |
5522620d0d2a7c2d8a337235ed74d7f59c8940314692ee02f94bdac4b89d0932
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.3
|
Release files / smelt_gpu-0.2.2-py3-none-any.whl
| Download URL | smelt_gpu-0.2.2-py3-none-any.whl |
|---|---|
| Size | 26.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
f89aea47a5b2438b827c3c90d098a210f0f55261817384fcbb1b7bd7c4481726
|
|
BLAKE2b-256 checksum How to use checksums |
f3f013bee7fe3f20277cf7b254b35a2308feaf08c9c5e2c970134f107873ecef
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.3
|
Security for smelt-gpu 0.2.2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.