shimmy
⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.
- Latest release
- 4h ago
- Releases
- 21
- Known CVEs
- 0
- First release
- Sep 04, 2025
- License
- MIT
- Downloads
- 12.2k
Repository
Source
- Stars
- 5.4k
- Forks
- 510
- Open issues
- 11
- Language
- Rust
- llama
- llamacpp
- llm-inference
- ollama-api
- command-line-tool
- gguf
- inference-server
- local-ai
Security score
No OpenSSF Scorecard available for this repository.
Packages from this repo
No other tracked packages from this repository.
Insights
Activity
- Total releases
- 21
- Last 12 months
- 21
- Cadence
- ~2 days
- Dependencies
- 36
Releases per month
last 12 monthsRelease mix
- major 2
- minor 9
- patch 9
21
releases
Dependencies
Depends on
2.2.0-
airframe
^0.2.2
-
anyhow
^1
-
assert_cmd
^2
dev
-
async-trait
^0.1
-
axum
^0.7
-
bytes
^1
-
chrono
^0.4
-
clap
^4
-
criterion
^0.5
dev
-
dirs
^5.0
1–10 of 36
Used by
Nothing tracked depends on this yet.
Releases
| Version | Released | |
|---|---|---|
2.2.0
minor
| ||
2.0.1
patch
| ||
2.0.0
major
| ||
1.9.0
minor
yanked
| ||
1.8.2
patch
yanked
| ||
1.8.1
minor
| ||
1.7.4
patch
| ||
1.7.3
patch
| ||
1.7.0
minor
| ||
1.6.0
minor
| ||
1.4.2
patch
| ||
1.5.1
minor
| ||
1.4.1
patch
| ||
1.4.0
minor
| ||
1.3.5
patch
| ||
1.3.4
patch
| ||
1.3.3
minor
| ||
1.2.0
minor
| ||
1.1.0
major
| ||
0.1.1
patch
|
1–20 of 21