Dosu
Dosu moved from maintaining your repo to measuring what your coding agents actually did.
Comparison · ai-assistants
recipes vs vLLM
A side-by-side editorial comparison of recipes and vLLM — release velocity, themes, recent moves, and the top alternatives to consider.
recipes vs vLLM: at a glance
What is recipes?
tidymodels' preprocessing engine learned sparsity, then settled into deprecations.
recipes is at 1.3.3, whose entire changelog is one suggested-package declaration. The substantive release in the window is 1.2.0, which taught recipe, prep and bake to work with sparse tibbles and sparse matrices, added a sparse argument to eight dummy and indicator steps, and made seventeen more steps preserve sparsity they receive. Since then the work has been deprecations and bug fixes.
What is vLLM?
Ships stable 0.27 while the rc trains grind through disaggregated-serving correctness.
vLLM's feed is release tags whose bodies are a single cherry-picked commit, so what is visible is the maintenance surface rather than headline features. The last six tags span the 0.24 through 0.27 lines, with fixes concentrated in disaggregated prefill/decode (P/D), speculative decoding, and the Transformers modelling backend. Hardware breadth is the other constant: TPU, ROCm, CPU/ARM and CUDA graph paths all show up across six entries.
recipes vs vLLM: editorial side-by-side
recipes
0.0AI-ASSISTANTS
tidymodels' preprocessing engine learned sparsity, then settled into deprecations.
◆ Current state
recipes is at 1.3.3, whose entire changelog is one suggested-package declaration. The substantive release in the window is 1.2.0, which taught recipe, prep and bake to work with sparse tibbles and sparse matrices, added a sparse argument to eight dummy and indicator steps, and made seventeen more steps preserve sparsity they receive. Since then the work has been deprecations and bug fixes.
◆ Where it's heading
The direction is consolidation of a large step catalogue rather than growth. step_select and step_nnmf have entered deprecation, arguments across nine steps moved from strings and vars() calls to bare names, and all steps now require the same four arguments. The sparse work stands as the last structural change; what follows tidies the surface around it.
◆ Prediction
With step_select mid-deprecation and step_nnmf newly deprecated in favour of step_nnmf_sparse, the next release most likely advances those deprecations rather than adding steps.
vLLM
5.0AI-ASSISTANTS
Ships stable 0.27 while the rc trains grind through disaggregated-serving correctness.
◆ Current state
vLLM's feed is release tags whose bodies are a single cherry-picked commit, so what is visible is the maintenance surface rather than headline features. The last six tags span the 0.24 through 0.27 lines, with fixes concentrated in disaggregated prefill/decode (P/D), speculative decoding, and the Transformers modelling backend. Hardware breadth is the other constant: TPU, ROCm, CPU/ARM and CUDA graph paths all show up across six entries.
◆ Where it's heading
The pattern points at hardening multi-node serving rather than adding user-facing surface. P/D under a data-parallel supervisor, KV-load lookahead for MTP speculative decoding, and CUDA graph correctness in the Transformers backend are all plumbing for large deployments. Each minor line ships several rcs before a stable cut, so the release stream reads as a stabilization funnel rather than a feature cadence.
◆ Prediction
Expect the 0.27 line to open its own rc series carrying more P/D and speculative-decoding fixes. The entries do not show enough to say which model families or hardware targets land next.
Alternatives to recipes and vLLM
Other ai-assistants products tracked by Sparkpulse, ranked by recent ship velocity. Each card links to a full editorial trajectory and lets you pivot into a head-to-head comparison with either recipes or vLLM.
GitHub Copilot
Copilot is standardizing the agent plugin layer while its model bench keeps rotating.
rsample
tidymodels' resampling package is retiring its old splitters for sliding windows.
imbalanced-learn
The resampling companion to scikit-learn now ships mostly to stay compatible with it.
parsnip
parsnip added a whole new regression type, then wired R models to JAX and PyTorch
mlr3
mlr3 is hardening the seams where its abstractions meet real learners
See all recipes alternatives → · See all vLLM alternatives →
Recent activity from recipes and vLLM
Latest ship moves from both products, interleaved chronologically. ⚡ = editorial spark.
- 2d agovLLMv0.27.0 — TPU compile fix for Kimi's vision tower
- 16d agovLLMv0.26.1rc0 — ROCm CI correctness reference fix
- 1mo agovLLMv0.25.0rc3 — P/D KV-load lookahead fix under MTP speculative decode
- 1mo agovLLMv0.25.0rc2 — embed scaling and CUDA graph fixes in Transformers backend
- 1mo agovLLMv0.25.0rc1 — flaky ARM ShortConv prefill test fix
- 1mo agovLLMv0.24.0rc2: Fix P/D with DP Supervisor (#46628)
- 2mo agorecipesDeclares mixOmics as a suggested package
- 4mo agorecipesstep_nnmf() deprecated in favour of step_nnmf_sparse()
- 1y agorecipesFixes tune_args() with tuned parsnip arguments
- 1y agorecipesBare-name arguments across nine steps; step_select() deprecated
- 1y agorecipesFixes sparsity steps applied to derived variables
- 1y agorecipesSparse tibbles and sparse matrices supported end to end ⚡
Frequently asked questions
What is the difference between recipes and vLLM?
They serve adjacent needs but don't currently overlap on shipped themes. vLLM is currently shipping more aggressively (velocity 5.0 vs 0.0), with 0 editorial sparks in the last 30 days against 0. See the at-a-glance table above for a side-by-side breakdown of velocity, recent sparks, and editorial themes.
Is recipes better than vLLM?
Sparkpulse doesn't pick a winner — we score release velocity, not feature parity. vLLM is currently shipping more aggressively (velocity 5.0 vs 0.0), with 0 editorial sparks in the last 30 days against 0. For your specific use case, the alternatives sections above list other ai-assistants products to evaluate alongside.
What are the best alternatives to recipes?
Top recipes alternatives in ai-assistants are ranked by recent ship velocity. Browse the "recipes alternatives" section above for the current picks, or visit /alternatives/recipes for the full list with editorial commentary on each.
What are the best alternatives to vLLM?
Top vLLM alternatives in ai-assistants are ranked by recent ship velocity. Browse the "vLLM alternatives" section above for the current picks, or visit /alternatives/vllm for the full list with editorial commentary on each.