Results for “parallel-inference”
27 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
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
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
More results
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
tangchunwu ultrawork
Parallel execution engine for high-throughput task completion
1
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
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
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
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
k-dense-ai dask
Scale pandas and NumPy workflows to larger-than-memory datasets using parallel and distributed computing.
30.2k · bundle
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
curiositech hoare-1978-csp
Foundational theory for process-oriented concurrency through synchronous message-passing, applicable to multi-agent coordination and parallel decomposition
10 · bundle
seaworld008 rally
Orchestrating multi-session parallel execution via Claude Code Agent Teams API and Codex CLI Subagents — launch, manage, coordinate concurrent tasks. Use when parallel work is needed.
65 · bundle
inference-sh python-sdk
Build AI applications with the inference.sh Python SDK: run apps, build agents, and integrate with 250+ models using sync/async, streaming, file uploads, and a tool builder API.
584 · bundle
orchestra-research training-llms-megatron
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies for maximum GPU efficiency.
10.4k · bundle
q2805187159 serving-llms-vllm
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
3 · bundle
akillness deep-research
Routes a research topic through a structured two-phase workflow: generate an extensible outline, then fan out parallel web-search agents to investigate each item into validated JSON, producing a complete markdown report with table of contents.
42 · bundle
neekware agenthub
Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric or LLM judge, and the best branch is merged. Use when: user wants multiple approaches tried in parallel — code optimization, content variation, research exploration, or any task that benefits from parallel competition. Requires: a git repo.
0 · bundle
tianhao909 serving-llms-vllm
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
1 · bundle
qcmuu serving-llms-vllm
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
0 · bundle
ichichuang serving-llms-vllm
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
0 · bundle
tianhao909 moe-training
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.
1 · bundle
qcmuu moe-training
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.
0 · bundle