jayleaton/deepseek-v41-tensorfold-spark
DeepSeek-V4.1-Flash on 2x NVIDIA DGX Spark with the TensorFold engine: 1.8-1.9x code, 2.5x multi-stream, 1.7-1.95x prefill vs the vLLM kit, exact speculative decoding. Work in progress.
🔌 Network
undeclared
⏳ Sandbox
untested
Who this is for
- developers using DSH for coding with Git workflows
下载量 / Downloads
0
Install
dsh plugin --profile web add jayleaton/deepseek-v41-tensorfold-spark
Sandbox test
This plugin has not been tested yet. Submit a test →
Links
Frequently asked
How do I install jayleaton/deepseek-v41-tensorfold-spark?
Run
dsh plugin --profile web add jayleaton/deepseek-v41-tensorfold-spark in DSH, or paste the package name into the DSH Desktop plugin page.What if it fails to install?
Check your DSH version first (
dsh --version), then look at the first error in the test-results section. If it still fails, open an issue on the repository.How do I uninstall it?
Run
dsh plugin --profile web remove jayleaton/deepseek-v41-tensorfold-spark.Same category
Compare with peers
| Plugin | Downloads | Verdict | Size |
|---|---|---|---|
| @michengai/dsh-skills-manager | 174.8K | pass | 262.02 MB |
| dsh-unlag | 59.4K | pass | 0.37 MB |
| @michengai/dsh-simplify | 15.1K | pass | 11.51 MB |
| dsh-plugin-toolkit | 11.3K | pass | 0.42 MB |
| dsh-mcp-registry | 10.0K | install_failed | — |
| huaweicloud-devkit | 9.3K | pass | 4.45 MB |
| dsh-plugin-health | 9.1K | pass | 2.01 MB |
| dsh-mcp-panel | 8.5K | pass | 16.85 MB |