throttle
Find and prove inference savings on your own GPUs: $/M tokens with 95% CIs, agent workloads, verified-savings statements. vLLM, SGLang, Ollama, LMDeploy.
KushagraKanaujia/throttle
View on GitHub ↗Find and prove inference savings on your own GPUs: $/M tokens with 95% CIs, agent workloads, verified-savings statements. vLLM, SGLang, Ollama, LMDeploy.
throttle ranks 313th of 313 in Observability & Tracing, actively maintained, last commit yesterday.
Star trajectory
18 days tracked2026-10-087 stars today2026-10-25
Momentum
- in 30d, below the Observability & Tracing median of +1.0%.
Maintenance
Last commit yesterday, fresher than the median of 5d.
How it compares in Observability & Tracing
throttle
7
stars
- 30d
commit yesterday
Observability & Tracing median
343
stars
+1.0% 30d
commit ~5d ago
Leader · langfuse
36.4k
stars
+3.9% 30d
commit today
Ranked 313th of 313 by stars.
- Language
- Python
- License
- MIT License
- Contributors
- 9
- Forks
- 6
- Watchers
- 0
- Open issues
- 12
- Releases
- 9
- Created
- 2026-08-17
- Stars this week
- +0
You've seen where throttle stands today.
Get the moves before everyone else: the 5 Observability & Tracing repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.