48
rllm-worker
v0.1.5 ExperimentalDevice worker, model runner, batch building, and CUDA graph capture for rLLM
Apache-2.0 Edition 2024 MSRV 1.85
Quick Verdict
- โActively maintained (updated 58d ago)
- !Pre-1.0: API may have breaking changes
- โPermissive license (Apache-2.0)
Security
Checking security advisories...
Downloads
371
Dependents
15
Releases
6
Size
44KB
Deep Insights
๐
Download decline
60 downloads in the last 30 days, down 33% from the previous period. May indicate migration to alternatives.
๐
Compact crate
At 43KB, rllm-worker is lightweight. Small crate size correlates with focused, well-scoped functionality.
๐
Used by top crates
Notable dependents include rllm-executor, rllm-server, rllm-bench. When high-quality crates choose rllm-worker, it's a strong quality signal.
Health Breakdown
Maintenance 17/25
Recency, release consistency, active ratio
Quality 15/25
Yanked ratio, deps, size, maturity, features
Community 4/20
Reverse deps, ownership, ecosystem
Popularity 3/15
Downloads, momentum, growth trend
Documentation 9/15
Docs, repo, license, metadata
Download Trend
Daily downloads ยท last 90 days
0/day avg
Top Dependents
Most downloaded crates that depend on rllm-worker
Version Adoption
v0.1.5
37%
v0.1.2
28%
v0.1.3
16%
v0.1.4
11%
v0.1.1
8%
Release Timeline
6 releasessince 2026
J
F
M
A
M
J
J
A
S
O
N
D
2026
6
LessMore
Feature Flags
default =["candle-backend"]
cpucudacandle-backend*experimental-tp
README
Loading README...
Maintainers
Dependencies
15
direct dependencies
Dependents
15
crates depend on rllm-worker