22 个 · 按相关度排序
Triage incorrect MNN outputs and regressions by matching symptoms to focused debugging guides. Use backend comparisons, minimal reproductions, and controlled experiments to investigate memory issues, quantization, concurrency, numeric limits, caches, and inconsistent results across runs.
中文简介正在准备中。当前显示英语简介。
Helps configure and troubleshoot DeepSpeed for training large models across multiple devices. Covers memory optimization, parallel training, and DeepNVMe storage transfers, with examples for tuning data movement and configuring models that divide work among specialized components.
中文简介正在准备中。当前显示英语简介。
Diagnose errors and incorrect inference results in MNN's QNN backend for Qualcomm HTP processors. Compare intermediate calculation data against CPU results to locate the first faulty operator, distinguish bugs from precision limits, and guide operator support and performance fixes.
中文简介正在准备中。当前显示英语简介。
Implement and troubleshoot large-model training with DeepSpeed across multiple GPUs. The skill covers memory optimization, parallel training, and numerical precision choices, alongside examples for storage transfers and models that divide work among specialized components.
中文简介正在准备中。当前显示英语简介。
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention
中文简介正在准备中。当前显示原文说明。
Develop lightweight CUDA operations for SGLang using JIT, which compiles code on first use. A tensor-scaling example explains implementation conventions, input validation, memory access helpers, and when to choose this approach.
中文简介正在准备中。当前显示英语简介。
Add a CUDA/C++ GPU operation to sgl-kernel using AOT, meaning compilation before use. Follow the implementation through PyTorch registration, Python API exposure, SGLang integration, correctness tests, and benchmarks that account for cache reuse.
中文简介正在准备中。当前显示英语简介。
Build safety checks for LLM prompts and responses using Meta's LlamaGuard moderation model. Classify potentially harmful content, block flagged messages, serve checks through an API, and integrate them with NeMo Guardrails.
中文简介正在准备中。当前显示英语简介。
Reduce the memory needed to run large language models with GPTQ quantization, which stores model weights at lower precision. Covers loading compressed models, quantizing your own models, choosing execution backends, and connecting to memory-efficient fine-tuning.
中文简介正在准备中。当前显示英语简介。
Adapt PyTorch training scripts for multiple GPUs or machines with Accelerate. This skill guides code changes, configuration, and launch commands, including mixed precision, which combines numerical formats, and DeepSpeed or FSDP integration for distributed training.
中文简介正在准备中。当前显示英语简介。
Adapt existing PyTorch training scripts to run across multiple GPUs or machines with Accelerate. This skill covers device setup, distributed training configuration, and mixed precision, which uses lower-precision numbers to reduce memory use.
中文简介正在准备中。当前显示英语简介。
Compress large language models to 4-bit weights to reduce GPU memory needs and accelerate text generation. Covers loading compressed models, converting your own models, choosing settings, and preparing memory-efficient fine-tuning with transformers and PEFT.
中文简介正在准备中。当前显示英语简介。
Guides PyTorch model training and fine-tuning, from choosing architectures to configuring optimizers and learning rates. Provides troubleshooting steps for unstable loss and memory shortages, plus methods for improving GPU throughput and comparing experiments.
中文简介正在准备中。当前显示英语简介。
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
中文简介正在准备中。当前显示原文说明。
Use when working on imp's quantization formats, loaders, or dequant paths - GGUF Q4_0...Q8_0/Q*_K/IQ4/MXFP4, NVFP4 two-level scaling (Modelopt vs compressed-tensors layouts), FP8 E4M3, StorageTier, decode cache, KV-cache dtypes (auto/fp16/fp8/int8/int4/nvfp4/mxfp4), "which quant should I use", "which KV dtype", scale-factor layout, dequant kernel wiring, imp-quantize / AWQ, judging quant quality (PPL). Do NOT use for writing/optimizing GEMM/GEMV kernels (sm120-cuda-expert) or measuring quant perf (benchmark-cuda).
中文简介正在准备中。当前显示原文说明。
Use when writing, reviewing, or optimizing CUDA kernels targeting sm_120a (RTX 5090 / Consumer Blackwell, GB202) in the imp inference engine. Triggers on CUDA/PTX kernel code, shared-memory layout, bank conflicts, tensor-core MMA (mxf4nvf4, tf32, 3xTF32/3xFP16), GEMV/GEMM/attention/quantization/GDN-scan kernels, decode tok/s under expected, kernel emitting HMMA instead of mxf4nvf4, occupancy, register pressure, __launch_bounds__, spills, PDL. Pair with `benchmark-cuda` for measurement and `check-degeneration` after hot-path changes.
中文简介正在准备中。当前显示原文说明。
Quantização pós-treinamento em 4-bits para LLMs com perda mínima de precisão. Use para implantar modelos grandes (70B, 405B) em GPUs de consumo, quando você precisa de redução de memória 4× com <2% de degradação de perplexidade, ou para inferência mais rápida (aceleração de 3-4×) vs FP16. Integra com transformers e PEFT para fine-tuning QLoRA.
中文简介正在准备中。当前显示原文说明。
API de treinamento distribuído mais simples. 4 linhas para adicionar suporte distribuído a qualquer script PyTorch. API unificada para DeepSpeed/FSDP/Megatron/DDP. Posicionamento automático de device, precisão mista (FP16/BF16/FP8). Config interativo, comando de launch único. Padrão do ecossistema HuggingFace.
中文简介正在准备中。当前显示原文说明。
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
中文简介正在准备中。当前显示原文说明。
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
中文简介正在准备中。当前显示原文说明。
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
中文简介正在准备中。当前显示原文说明。
Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.
中文简介正在准备中。当前显示原文说明。