Registry › Compare › LiteLLM vs vLLM

LiteLLM vs vLLM

vLLM leads on trust: 81.5/100 (Grade A) against 77.8/100 (Grade B), a 3.7-point gap. LiteLLM leads on adoption; vLLM leads on supply-chain integrity and transparency.

B LiteLLM 77.8

The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]

BerriAI/litellm · #178 overall · #3 LLM Gateways & Infra · coverage A (4/5)

Choose LiteLLM if adoption matters most.

+0.6Adoption: 22.6M weekly downloads against 441.3k

A vLLM 81.5

A high-throughput and memory-efficient inference and serving engine for LLMs

vllm-project/vllm · #129 overall · #2 LLM Gateways & Infra · coverage A (4/5)

Choose vLLM if supply-chain integrity and transparency matter most.

+1.4Safety / Integrity: OSSF Scorecard 6.9 against 5.8
+1.0Transparency: OSSF Scorecard 6.9 against 5.8

Where they differ

12.2

Safety / IntegrityvLLM +1.4

13.6

13.4

TransparencyvLLM +1.0

14.4

20.0

MaintenanceLiteLLM +0.1

19.9

20.0

AdoptionLiteLLM +0.6

19.4

+1.4

Runtime calibrationvLLM +2.0

+3.4

1 dimension identical: Identity 10.8 · Full evidence table

An independent, evidence-based trust comparison of LiteLLM and vLLM, two LLM Gateways & Infra projects in the HVTracker registry. Scores come from public, checkable signals — supply-chain provenance, OSSF Scorecard, maintenance, and adoption — not popularity.

Full evidence

Signal	LiteLLMBerriAI/litellm	vLLMvllm-project/vllm
HVTrust score	77.8	81.5
Evidence grade	B	A
Coverage grade	A	A
Overall rank	#178	#129
Rank in LLM Gateways & Infra	#3	#2
GitHub stars	59.8k	92.9k
Last updated	today	1d ago
Build provenance	No	No
OSSF Scorecard	5.8 / 10	6.9 / 10
License	NOASSERTION	Apache-2.0
Downloads	22.6M/wk	441k/wk
Trust dimensions (points earned)
Safety / integrity / 25	12.2	13.6
Identity & provenance / 18	10.8	10.8
Transparency / 17	13.4	14.4
Maintenance / 20	20.0	19.9
Adoption / 20	20.0	19.4
Runtime capability surface (full matrix)
MCP server	Implemented	Declared
External providers	7 — Amazon Bedrock, Anthropic, Google Gemini, …	—
Requires API keys	Yes	No
Plugin surface	plugins	extensions
Provenance drift	Match	Match

Open in the live compare tool → LiteLLM profile vLLM profile More LLM Gateways & Infra →

How to read this: HVTrust (0–100) weighs supply-chain signals (provenance, OSSF Scorecard, signed commits, open license) alongside real-world adoption, scaled by an evidence-confidence factor. Grade bands: A ≥ 80, B ≥ 65, C ≥ 50, D < 50. Signals refresh daily. Full methodology v4.3 →