Discover latest generative AI models, prompt engineering papers, and MCP servers

Menu Close

首页
data
training
models
inference
context
prompt
mcp
agents
关于

嗯，目前共计290篇文章

2021

4月 09, 2021

在GPU集群上使用Megatron-LM高效训练大规模语言模型

Search for:

标签云

0528-update 2-bit量化 3-bit-4-bit 3d-parallelism 4-bit-quantization 405b 671b 70b 8-bit训练 ACE框架 AI代理 AI加速器 Agent架构 Attention优化 Blackwell GPU CUDA kernel ChatGPT CoT-limitations Continuous Batching D-最优设计 DPO DSPy DeepSeek DeepSeek R1 Development Direct Preference Optimization Dueling Bandit FLOPs优化 FP4量化 FlashAttention FlashInfer GPTQ GPU加速 GUI导航 GraphRAG H20 GPU Hadamard变换 Hadamard旋转 K-means聚类 KV Cache KV Cache量化 KV缓存 KV缓存优化 KV缓存压缩 Kernel优化 LLM Alignment LLM Serving LLM serving LLM-as-judge LLM加速 LLM局限性 LMS3方法 LoRA MCTS MIPRO MLA Megatron-LM Multi-Head Latent Attention ORM Official OmegaPRM OpenAI o1 PEFT PPO PRM PagedAttention Preference Learning Productivity Prompt Engineering RAG综述 RLHF ReAct SGLang Search Speculative Decoding Survey Tensor Core Test-Time Compute Token优化 WGMMA WebScraping accessibility acting adaptive-alignment adaptive-reasoning african-languages agent agent-model agent-optimization agentcore agentic-ai ai ai-agents ai-automation ai-feedback ai-search ai4bharat aleph-alpha alerting alibaba alignment-methods alternative-paths analogical-prompting analogical-reasoning anthropic any-to-any apache-2.0 ape api apm arithmetic-reasoning assessment atlas atmospheric-science attention-budget attention-mechanism attention优化 audio audio-model automate-cot automated-annotation automatic-cot automatic-optimization automatic-prompt-engineering automatic-prompt-generation automatic-prompt-optimization automation autoregressive aws baas backtracking banking batched-generation beam-search bedrock biology biomedical-ai biosurveillance brave browser browser-automation cache category-theory chain-of-thought chat chat-model chemistry ci-cd claude claude-3.5 claude-4 claude-4.5 climate clip cloud cluster-management code-agent code-intelligence code-management code-quality code-review code-search coding coding-model collaboration commercial communication comparative-study compositional-generalization comprehensive comprehensive-review computational-efficiency compute-scaling computer-use consensus containers content-extraction context-engineering context-management contrastive-filtering controlled-experiments convertapi convolution copilot cost-aware-optimization cost-effective cost-efficient cot cpu-offload critical-analysis cultural-ai custom kernel cypher damo data-access data-commons data-distribution data-parallel data-parallelism data-processing database datadog debugging decoding-strategies decoding-strategy decomposed-prompting decomposition deep-reasoning deepseek deepseek-r1 deepseek-v3 deepspeed deliberate-reasoning demonstration-selection derivative-free-optimization development devops devtools diagnostic-imaging diffusion distributed-training document-database document-processing documentation domain-adaptation domain-specific double-quantization drug-discovery dynamic-prompt-refinement e-commerce e-learning earth-observation ecmwf ecommerce edge-ai edge-deployment education educational-data efficiency efficient elasticsearch embeddings emergent-abilities ensemble-method enterprise entities entity-extraction equall error-correction error-tracking european-ai evaluation-methods evo-cot evolutionary-merge evolutionary-methods experimental extended-thinking external-memory factual-accuracy factual-generation fast-inference few-shot few-shot-learning few-shot-reasoning file-converter finance fine-tuning fintech flan flash-attention flava formal-verification format-conversion foundation-model foundation-models fp8 free-tier french fsdp full-text-search function-calling gates gdpr-compliant gemini gemini-2.0 gemma gemma-3 gemma-3n generalization genomic-ai german git github glm gnn go google got gpt-3 gpt-4o gpt-5 gpt-5-pro gpu-optimization gradient-based-optimization gradio grafana granite graph-database graph-of-thoughts graph-rag graph-retrieval graph-structured-knowledge greedy-vs-exploration grok grpo gui-navigation h100 hashicorp hausa healthcare hessian-ai heuristic-sampling high-throughput hindi html-parser http-client huggingface human-feedback hunyuan hybrid-architecture hyena iac ibm image-conversion image-editing image-generation image-text-pairs image-to-image image-understanding imo-gold implicit-reasoning in-context-learning inclusionai indic-languages indonesian inference-optimization infinite-context influxdb infrastructure instruct instruct-model instruction-guided instruction-optimization instruction-tuning intermediate-computation internlm intrinsic-reasoning iot iterative-refinement janus japanese java joint-optimization knowledge-base knowledge-graph knowledge-intensive knowledge-management kv-cache language-model-programs language-models large-scale-corpora latency-reduction latent-capabilities latent-reasoning law leap learning-from-mistakes least-to-most-prompting legal legal-ai lfm2 ling liquid-ai liquidai llama llama-3.1 llama-3.3 llama-4 llm llm-agents llm-as-optimizer llm-evaluation llm-generation llm-optimization lmarena lms loki long-context long-context-processing long-cot-reasoning low-latency low-resource magistral mamba markdown markdown-conversion matformer math mathematical-reasoning mathematics matrix-decomposition mcp mcp-server media-conversion medical-ai megatron-lm meilisearch memory memory-management memory-optimization messaging meta meta-ai meta-learning meta-policy-optimization meta-prompt meta-prompting metagenomic methodology metrics microsoft mistral mistral ai mistral-based mistral-small mit-license mixtral mixture-of-experts ml model-compression model-confidence model-merging model-scaling modular-prompting moe molecular-science mongodb monitoring monte-carlo-estimation mosaicml multi-agent multi-hop-reasoning multi-llm multi-scale-support multi-stage-optimization multi-step-reasoning multi-step-tasks multi-task-learning multiagent-systems multilingual multimodal multimodal-prompting mysql n8n nasa natural-language natural-language-optimization needle-in-haystack nemotron neo4j news-search nf4 nlp-tasks non-transformer nosql notion nvidia o1 o1-mini observability observations official omni-modal on-device oncall one-shot-quantization open-source open-source-models open-weights openai openhathi operational-ai opro optimization-theory opus out-of-distribution outlier抑制 paged-optimizers pandemic-monitoring parallel-compute parallel-decoding parallel-thinking parameter-driven-methods parameter-free-methods passage-retrieval pattern-matching payments pe2 persistence phd-level phi-4 physics pipeline-parallelism planning playwright post-training-quantization postgres postgresql ppo pre-training preference-learning principle-learning problem-solving process reward model process-reward-models process-supervision productivity progressive-quantization prometheus prompt-engineering prompt-engineering-survey prompt-optimization prompt-optimization-toolkit prompt-selection prompt-self-optimization prompt-space prompting-methods proprietary protocol prover pseudo-demonstrations public-data public-health pubmed python pytorch qdrant qlora quantization quantization-finetuning question-answering qwen qwen3 rag rag-benchmarks rag-datasets rational-chain-generation react real-time real-time-search reasoning reasoning-emergence reasoning-evaluation reasoning-limitations reasoning-model reasoning-scaling reasoning-without-prompting recurrent-architecture redis reference reflection reinforcement-learning relations repository research retail retrieval-augmented-generation reward-hacking-prevention reward-model-optimization reward-modeling rlaif rlhf rust safety sakana-ai scaling-laws scientific-ai scientific-computing scratchpad screenshot-html search search-agent search-algorithms search-engine security self-adaptive-prompting self-consistency self-feedback self-generation self-improvement self-refine self-rubrics semantic-search sentry sequential-thinking serper-api serverless sitemap skeleton-of-thought slack small-but-capable small-language-model small-model smaller-models social-media software-engineering sonarqube sonnet southeast-asian-languages sovereign-ai sparse-attention speech-generation speech-recognition sql sqlite sqlserver stagehand stanford state-space-model static-analysis statistics step-by-step structural-prompting structure-aware-generation structured-thinking sub-task-delegation subgraph-extraction supabase supervised-fine-tuning survey sustainability swahili symbolic-reasoning synthetic-data task-decomposition task-loss-gradients taxonomy team-collaboration telegram telethon tencent tensor-cores tensor-parallelism terraform test-time compute test-time-compute test-time-reasoning testing text-feedback-optimization text-to-image thai theorem-proving theoretical-analysis theoretical-framework thinking-mode thinking-model thought-generation time time-series timezone together-ai token-optimization tool-calling tool-use top-k-decoding transformer-llms tree-of-thoughts trillion-parameter tts type-theory typescript unified-framework unified-model unified-system upstash usp utility vLLM vLLM优化 vcs vector-search verifiable-rewards version-3.2 version-control video video-understanding vietnamese vision vision-language vision-language-models visual-prompting voice-ai voxtral w4a8kv4 weather weather-forecasting web-agent web-research web-scraping web-search web-task web-ui webscraping woocommerce wordpress workflow-automation workspace x-platform xai xhosa yoruba zero zero-offload zero-shot zero-shot-learning zhipu-ai zulu 上下文一致性上下文优化上下文学习上下文工程上下文窗口上下文管理专家选择个性化主动学习事件分割事实准确性人类反馈人类可读提示人类认知模型代理架构代码生成任务分解任务无关优化局限性低代码平台低比特量化低精度推理偏好学习元提示内存优化内存管理分布式训练动态结构构建动态路由动态适应即时编译参数高效微调反思机制合成边界案例向量量化吞吐量优化吞吐量提升图RAG 图像描述图检索图检索增强生成图神经网络在线学习块稀疏格式基于AI反馈的强化学习基准测试多专家多任务学习多任务理解多模态偏好学习多模态理解多跳推理多适配器多重记忆系统大型语言模型大型语言模型提示优化大语言模型奖励模型实际能力宪法AI 宪法AI对齐对比学习对话对话对齐对齐少样本学习层级索引复用工作负载均衡工具调用工具链幻觉缓解幻觉问题开放式任务弹性并行强化学习思维链思维链微调性能优化性能监控性能评估性能边界情节记忆成本高效投机解码拒绝机制指令遵循指向定位推测解码推理推理优化推理加速推理增强推理局限性推理时扩展推理时计算推理迁移提示优化提示优化分析提示工程提示框架提示模式提示重写教育内容合成数学推理数据中心部署文本生成无参考优化无标注学习无监督学习无限上下文显存优化智能体查询中心校准过程样本效率样本选择梯度优化梯度检查点检索增强生成模块化框架模型压缩模型架构步骤级监督注意力优化流水线并行测试时优化测试时扩展混合专家模型理论分析用户建模用户意图对齐直接偏好优化知识图谱知识密集型任务知识蒸馏硬件加速示例选择离线学习稀疏注意力端到端优化粒度优化系统架构线性校正结构化提示结果奖励模型综述论文脚手架自优化自动化优化自动提示优化自动提示工程自我批评自然语言理解自监督学习自适应学习自适应推理行为优化视觉-语言对齐视觉问答视角理解计数任务计算scaling 计算效率认知架构认知模型训练免费训练可视化记忆更新记忆检索记忆管理记忆膨胀记忆质量设计空间探索评估基准语义压缩语义块语言建模负样本学习负载均衡转置优化软件模式轻量级模型边缘设备过程奖励模型过程监督连续空间推理迭代优化配对比较采样策略错误分析长上下文长上下文推理长上下文训练长序列推理长文本推理长文本理解长期记忆长期运行问答预训练

归档

© 2025 Generative AI Discovery All Rights Reserved.

Theme by hiero