# vLLM (@vllm_project) on x

- id: koinon:creator:x_vllm_project
- url: https://koinonlink.com/kol/x/vllm_project
- schema_version: 1.4

## Identity
- platform: x
- handle: vllm_project
- platform_url: https://twitter.com/vllm_project
- website: https://vllm.ai
- entity_type: creator
- person_id: Cross-platform identity not resolved for this creator.

## Reach
- followers: 41829
- following: 36
- posts_total: 1060
- posts_observed: 1
- posts_per_day: 1.132
- account_age_days: 936
- verified: true
- size_tier: koc

## Engagement
- status: peak_post_only
- peak_post_engagement_rate: 0.00158
- best_post_interactions: 66
- measurement_source: x_post_interactions
- measurement_formula: interactions on one post — likes, or likes + reposts + replies depending on the discovery path (the two are not distinguishable in the stored data)
- comparable_pool: peak_interactions
- status_note: We have only the single best observed post, so no mean exists. peak_post_engagement_rate is an UPPER BOUND, systematically higher than an average — never compare it against an average rate.
- unit_note: engagement_rate and peak_post_engagement_rate are ratios (0-1); avg_interactions_per_post and best_post_interactions are absolute counts. Read status before reading any number: a null rate has several different causes and status says which one applies here.

## Content
- category: software
- subcategory: devtools
- category_confidence: 0.96
- category_source: derived_from_recent_content
- topics: LLM inference optimization, Edge deployment of small LLMs, Agentic AI systems, Hardware-agnostic LLM serving, vLLM framework usage, Low-resource LLM deployment
- bio: A high-throughput and memory-efficient inference and serving engine for LLMs. Join https://t.co/lxJ0SfX5pJ to discuss together with the community!

## Audience (inferred)
- status: present
- description: Developers and AI engineers building agentic systems and lightweight LLM inference on edge devices
- roles: dev
- seniority: practitioner
- pain_points: Struggling with high memory usage and low throughput when running small LLMs on edge devices, Having difficulty deploying LLMs across heterogeneous hardware (CPUs, NPUs, GPUs), Need efficient inference engines that support agentic workloads without sacrificing speed or memory efficiency
- posts_analysed: 7
- confidence: 0.4

## Commercial (inferred)
- audience_buyer_fit: 0.8
- promotion_intent: 0.8
- open_to_collaboration: false
- contact: Koinon does not publish creator contact details.

## Quality signals
- authenticity_score: 86
- authenticity_basis: engagement_observed
- credibility_score: 86
- flagged_for_review: false
- koinon_bd_grade: B — measures Koinon partner-outreach fit, not creator quality
- interpretation: Signals for triage, not verdicts. A flag means the profile is worth a manual check.

## Evidence
- [x_vllm_project#40cb19b4] 🚀 Day-0 support for  LFM2.5-230M on vLLM! (https://twitter.com/vllm_project/status/2070177937815736420)
- [x_vllm_project#5f125b7c] Ready to serve @liquidai's smallest LFM2 model for fast GPU inference and agentic workloads.
- [x_vllm_project#e4f3e7d8] 🧠 230M parameters, built on the LFM2 architecture
- [x_vllm_project#39886e56] 📚 Pre-trained on 19T tokens with 32K context
- [x_vllm_project#d49b7484] 🛠️ Designed for agentic tasks across phones, robots, home automation, and network automation devices
- [x_vllm_project#a2f54d40] ⚡ Built to run across CPUs, NPUs, and GPUs
- [x_vllm_project#94e84aa2] Congrats to the @li

## Provenance
Every inferred field below carries how it was produced. Facts stay facts; inferences stay inferences.

- audience.description: source_type=ai_inferred, confidence=0.4, freshness_days=21, method=llm_persona_from_recent_content
- audience.roles: source_type=ai_inferred, confidence=0.4, freshness_days=21, method=llm_persona_from_recent_content
- audience.seniority: source_type=ai_inferred, confidence=0.4, freshness_days=21, method=llm_persona_from_recent_content
- commercial.audience_buyer_fit: source_type=ai_inferred, confidence=0.6, freshness_days=79, method=llm_scorer — Relative signal within Koinon indexing, not a market-wide score.
- commercial.promotion_intent: source_type=ai_inferred, confidence=0.6, freshness_days=79, method=llm_scorer
- quality.anomaly_flags: source_type=heuristic, confidence=0.5, freshness_days=119, method=profile_snapshot_and_engagement_ratio_heuristic — Means "worth a manual check", NOT confirmed fraud. Flags can be wrong and are not a verdict about the person.
- quality.authenticity_score: source_type=heuristic, confidence=0.5, freshness_days=79, method=Profile-shape heuristic from a single snapshot (follower count, following ratio, account age, posting volume, verification), reduced for engagement red flags where post engagement was collected. Where only a follower count is available the score saturates at 58. — The input set differs by platform; do not compare this score across platforms.
- quality.koinon_bd_grade: source_type=ai_inferred, confidence=0.5, freshness_days=119, method=llm_partner_fit_classifier + fit_score >= 0.6 AND authenticity >= 60 => A; fit_score >= 0.4 AND authenticity >= 45 => B; else C. authenticity < 30 or a promotional-pattern flag => quarantine. — Koinon partner-outreach fit, not creator quality.
- reach.followers: source_type=observed, confidence=0.95, freshness_days=119, method=platform_profile

## Freshness
- profile_checked_days_ago: 119
- content_analysed_days_ago: 79
- audience_updated_days_ago: 21

## AI retrieval
- indexing_requests: 9
- user_triggered_requests: 0
- note: Being indexed in bulk is not the same as being retrieved to answer a question.

## This profile
- Claim or correct: https://koinonlink.com/claim?k=x_vllm_project
- Request removal: https://koinonlink.com/claim?k=x_vllm_project
- Terms: https://koinonlink.com/for-ai