跳到正文
cccskills

“efficient inference”的搜索结果

31 个 · 按相关度排序

High-throughput inference on FriendliAI — optimized serving engine for low-latency, cost-efficient LLMs.

中文简介正在准备中。当前显示原文说明。

aicodedecode/awesome-muse-skills242026年10月10日 更新

Build with DeepSeek's models — efficient open-weight reasoning models and low-cost API inference.

中文简介正在准备中。当前显示原文说明。

aicodedecode/awesome-muse-skills242026年10月10日 更新

Modelo de espaço de estados com complexidade O(n) versus O(n²) dos Transformers. Inferência 5× mais rápida, sequências de milhão de tokens, sem cache KV. SSM seletivo com design aware de hardware. Mamba-1 (d_state=16) e Mamba-2 (d_state=128, multi-head). Modelos 130M-2.8B no HuggingFace.

中文简介正在准备中。当前显示原文说明。

artubss/SKILLS-CLAUDE-CODE112026年5月17日 更新

Híbrido RNN+Transformer com inferência O(n). Tempo linear, contexto infinito, sem cache KV. Treina como GPT (paralelo), infere como RNN (sequencial). Projeto Linux Foundation AI. Produção em Windows, Office, NeMo. RWKV-7 (março de 2025). Modelos até 14B parâmetros.

中文简介正在准备中。当前显示原文说明。

artubss/SKILLS-CLAUDE-CODE112026年5月17日 更新

Quantiza LLMs para 8-bit ou 4-bit com redução de memória de 50-75% e perda mínima de acurácia. Use quando a memória GPU é limitada, precisa ajustar modelos maiores ou quer inferência mais rápida. Suporta formatos INT8, NF4, FP4, treinamento QLoRA e otimizadores 8-bit. Funciona com HuggingFace Transformers.

中文简介正在准备中。当前显示原文说明。

artubss/SKILLS-CLAUDE-CODE112026年5月17日 更新

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.

中文简介正在准备中。当前显示原文说明。

huang-sh/DeepScience42026年7月15日 更新

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

中文简介正在准备中。当前显示原文说明。

ibragimov-oasis/vibe-coder32026年6月24日 更新