Results for “parallel-inference”
62 skills
orchestra-research serving-llms-vllm
Deploy and serve LLMs with high throughput using vLLM's PagedAttention and continuous batching. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism for production inference.
10.4k · bundle
qhjqhj00 ray-data
Process large ML datasets in parallel across CPU or GPU clusters, with streaming execution, multi-format I/O, and integration with Ray Train, PyTorch, and TensorFlow for batch inference and preprocessing pipelines.
3 · bundle
brycewang-stanford causal-inference-mixtape
This skill should be used when the user asks to "implement a DiD regression", "write a causal inference pipeline", "set up an event study", "implement instrumental variables", "run a regression discontinuity design", "build a synthetic control model", "implement propensity score matching", "write parallel trends test", "implement Bacon decomposition", or needs code templates for causal inference methods in Python, R, or Stata. Based on Scott Cunningham's Causal Inference: The Mixtape.
1k · bundle
antigravity llm-council
Run Fireworks-hosted open-weight model councils that compare responses and synthesize a final answer.
42.4k · bundle
tianhao909 speculative-decoding
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.
1 · bundle
qcmuu speculative-decoding
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.
0 · bundle
More results
tianhao909 rwkv-architecture
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.
1 · bundle
bytesagain dask
Dask parallel computing reference for Python. Covers Dask DataFrame (parallel Pandas), Dask Array (parallel NumPy), Dask Delayed for custom parallelism, Dask Bag, distributed clusters, dashboard monitoring, and scaling best practices.
12 · bundle
dotnet build-parallelism
Optimize MSBuild build parallelism by configuring /maxcpucount, graph build mode, project references, and analyzing binlogs to reduce multi-project solution build times.
4k
0xharryriddle parallel
Only to be triggered by explicit /parallel-task commands.
3
qcmuu rwkv-architecture
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.
0 · bundle
lucassantana-dev parallel-phases
Execute phased plans with multiple independent tasks per phase by fanning out one agent per task, reconciling outcomes per wave, gating between phases with verify commands, and emitting a phase × outcome report. Triggers include "execute this plan", "work through these phases", "swarm over this backlog", "parallelize this plan".
1 · bundle
tangchunwu ultrawork
Parallel execution engine for high-throughput task completion
1
salacoste ultrawork
Parallel execution engine for high-throughput task completion
1
nivkazdan test-parallelizer
Test Parallelizer - Auto-activating skill for Test Automation. Triggers on: test parallelizer, test parallelizer Part of the Test Automation skill category. Use when writing or running tests. Trigger with phrases like "test parallelizer", "test parallelizer", "test".
4
k-dense-ai parallel-web
Search the web, extract URL content, enrich datasets with web-sourced fields, and run deep research reports, prioritizing academic and scientific sources.
30.2k · bundle
danstrem2 parallel-agents
Multi-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspectives.
2
artubss dask
Computação paralela/distribuída. Escale pandas/NumPy além da memória disponível, DataFrames/Arrays paralelos, processamento multi-arquivo, grafos de tarefas, para datasets maiores que RAM e workflows paralelos.
10 · bundle
metinduraktr-44 dask
Parallel/distributed computing. Scale pandas/NumPy beyond memory, parallel DataFrames/Arrays, multi-file processing, task graphs, for larger-than-RAM datasets and parallel workflows.
0 · bundle
tinh2 broadcast
Applies the same change across multiple repositories in parallel using git worktrees, tests, and pull requests.
13
whd4 parallel-agents
Multi-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspectives.
0
0xharryriddle parallel-task
Only to be triggered by explicit /parallel-task commands.
3
alterlab-ieu alterlab-pufferlib
Scales reinforcement learning with PufferLib — high-throughput parallel training (PuffeRL), vectorized environments, and native multi-agent systems achieving 2-10x speedups over standard implementations. Use when scaling RL to millions of steps per second, running vectorized or multi-agent setups, building custom PufferEnv tasks, or integrating game environments (Atari, Procgen, NetHack, PettingZoo). For standard single-agent algorithm implementations (PPO/SAC/DQN) or quick prototyping prefer alterlab-stable-baselines3. Part of the AlterLab Academic Skills suite.
60 · bundle
jackychenlu dask
Parallel/distributed computing. Scale pandas/NumPy beyond memory, parallel DataFrames/Arrays, multi-file processing, task graphs, for larger-than-RAM datasets and parallel workflows.
0 · bundle
haongo232 parallel-agents
Multi-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspectives.
3
nvidia tao-run-inference-service
Start, query, and stop a TAO inference microservice for a specific network architecture by delegating container execution to the appropriate platform skill.
2.2k · bundle
chen-yu-hao dask
Parallel/distributed computing. Scale pandas/NumPy beyond memory, parallel DataFrames/Arrays, multi-file processing, task graphs, for larger-than-RAM datasets and parallel workflows.
5 · bundle
k-dense-ai dask
Scale pandas and NumPy workflows to larger-than-memory datasets using parallel and distributed computing.
30.2k · bundle
diegosouzapw riff
Generates multiple app variations in parallel, each a distinct interpretation of a theme, then ranks them and presents a gallery.
54 · bundle
tianhao909 training-llms-megatron
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.
1 · bundle
lovits ultrawork
Parallel execution engine for high-throughput task completion
0 · bundle
kursku gsd-execute-phase
Execute all plans in a phase with wave-based parallelization
55
smith6jt-cop gpu-parallel-scheduling
GPU-safe parallel processing patterns for KINTSUGI to prevent OOM crashes and ensure Jupyter-compatible progress output
3
vvieira010-pixel curriculum-crosswalk
Compares two or more band-tagged frameworks and produces a framework-neutral topic matrix showing coverage and gaps across all inputs, plus an optional reference-centric PLC crosswalk document when a reference framework is supplied.
0
matlab matlab-set-up-worker-state
Set up worker environment and per-worker state for parallel pools. Use when code needs paths, environment variables, database connections, loaded libraries, or expensive objects available on workers before parfor/parfeval runs. Teaches parallel.pool.Constant, parfevalOnAll, and parpool name-value pairs. Also use when refactoring existing code that uses spmd for side-effect setup (an anti-pattern). Triggers: worker setup, pool constant, per-worker state, non-serializable, loadlibrary on workers, database connection parfor, addpath workers, spmd before parfor, worker environment, reduce parfor overhead, parfor setup, resource creation in parallel loop, cannot serialize error, undefined function or variable on workers error, load data per worker, reduce data transfer, parallelize setup, improve parallel code.
920 · bundle
curiositech hoare-1978-csp
Foundational theory for process-oriented concurrency through synchronous message-passing, applicable to multi-agent coordination and parallel decomposition
10 · bundle