Showing 120 of 120on this page. Filters & sort apply to loaded results; URL updates for sharing.120 of 120 on this page
[torch.distributed] Document bfloat16 support · Issue #75215 · pytorch ...
torch.fft.rfft: Unsupported dtype BFloat16 · Issue #117844 · pytorch ...
Does BFloat16 model training supported on ARC? · Issue #545 · intel ...
Implement torch.pow for float16 and bfloat16 on CPU · Issue #50789 ...
Add support for bfloat16 in torch.from_numpy() · Issue #101781 ...
Placing model on bfloat16 on CPU make it freeze/hang · Issue #75458 ...
Bfloat16 tensor .numpy() support · Issue #90574 · pytorch/pytorch · GitHub
BFloat16 datatype support in Quantization · Issue #111487 · pytorch ...
automatic bfloat16 conversion · Issue #1489 · pytorch/xla · GitHub
Empowering PyTorch on Intel® Xeon® Scalable processors with Bfloat16 ...
use bfloat16 on nvidia V100 GPU · Issue #124996 · pytorch/pytorch · GitHub
Bfloat16 training - mixed-precision - PyTorch Forums
Pytorch笔记：Float32 Float16 BFloat16 - 知乎
使用 Bfloat16 在 Intel® Xeon® 可扩展处理器上赋能 PyTorch – PyTorch - PyTorch 框架
Bfloat16 has worse performance than float16 for conv2d in Pytorch ...
Server - PyTorch BFloat16 “TypeError: Got unsupported ScalarType ...
Unlocking the Power of bfloat16 in TensorFlow: A Deep Dive for Python ...
Figure 2 from Bfloat16 Processing for Neural Networks | Semantic Scholar
dtypes of tensors: bfloat16 vs float32 vs float16 | by Manyi | Medium
TensorFlow 中的 bfloat16 数据类型 - 墨天轮
[1905.12322] A Study of BFLOAT16 for Deep Learning Training
float32 float16 bfloat16 推理训练GPU速度和内存调研_mindspore如何在gpu上用精度为float16的进行 ...
BFloat16 support · Issue #1290 · tinygrad/tinygrad · GitHub
float16과 bfloat16
Accelerating PyTorch Model Training
有关于pytorch单精度bfloat16位_torch.bfloat16-CSDN博客
Neural Network Quantization in PyTorch | Practical ML
Accelerating Generative AI with PyTorch: Segment Anything, Fast | PyTorch
Accelerating Generative AI with PyTorch: Segment Anything, Fast – PyTorch
Optimizing Memory Usage for Training LLMs and Vision Transformers in ...
Bfloat16_for_Pytorch/scripts/normal_addition_pt.py at master · JPGOMEZP ...
ValueError: torch.bfloat16 is not supported for quantization method awq ...
Model training with torch_dtype=torch.bfloat16 is possible? · Issue ...
PyTorch CPU性能优化（四）：BFloat16 - 知乎
使用 PyTorch 加速生成式 AI：Segment Anything, Fast – PyTorch - PyTorch 框架
Learning PyTorch - Jie Yu’s Home Page
pytorch 笔记：torch.optim.Adam-CSDN博客
Pytorch 如何选择半精度（BFLOAT16 vs FLOAT16）来训练你的模型|极客笔记
transformers 不同精度float16、bfloat16、float32加载模型对比_model weight dtype ...
Why is there such a huge performance gap between bfloat16, float16, and ...
Thread by @PyTorch on Thread Reader App – Thread Reader App
分布式训练中的BFloat16与Float16
[Training] Missing 'BFLOAT16' attribute in `torch._C._onnx ...
How to load bfloat (float16) weight into torchsharp model · Issue #1204 ...
深入理解浮点数：单精度、双精度、半精度和BFloat16详解 - 技术栈
load and train with bf16，saved torch_dtype is float32 · Issue #30305 ...
(a) Block storage and configuration for BFloat16; (b) the... | Download ...
Float32 vs Float16 vs BFloat16? - by Damien Benveniste
Float32, Float16 or BFloat16! | ABN Software
PygmalionAI/pygmalion-7b · Reasoning behind bfloat instead of float?
```python 2024-09-03 09:03:32 INFO unet dtype: torch.float8_e4m3fn ...
为什么很多新发布的LLM模型默认不用float16呢？ - 知乎
【Diffusers】Ideogram 4 をさっそく使ってみる - パソコン関連もろもろ
teolm30/fox-1.2-image · Hugging Face
MIN-Lab/minWM at main
nvidia/Cosmos-Predict2.5-2B at main
Muapi/cutaway-technical-drawing · Hugging Face
Muapi/tenjin-kotone-wan2.1-14b-t2v · Hugging Face
Muapi/rosemi-lovelock-wan2.1-14b-t2v · Hugging Face
Muapi/hoshimi-miyabi-zenless-zone-zero-goofy-ai · Hugging Face
stable-diffusion-v1-5/stable-diffusion-v1-5 at main
Muapi/reverse-upright-straddle-reverse-cowgirl-position-concept ...
Qwen3-TTS语音设计，克隆与生成 - 技术栈
kontext-community/relighting-kontext-dev-lora-v3 at main
FlutterGuyAzaza/Jiggly_Everything · Hugging Face
prompts.json · WaveCut/ideogram-4-sdnq-uint4 at main
FLUX.1-dev模型本地训练&推理教程（GPU/NPU）-CSDN博客
svdq-int4_r256-z-image-turbo.safetensors · nunchaku-ai/nunchaku-z-image ...
Muapi/kanae-wan2.1-14b-t2v · Hugging Face
jongking/LTX-2.3-Multiple-Subject-Reference · Hugging Face
thangvip/compliment-forest-moonlit-gouache-flux-lora-v2 · Hugging Face
black-forest-labs/FLUX.1-Redux-dev at main
Muapi/welcome-to-test-this-elsa-hidream-wan2.2-1-hunyuan-flux · Hugging ...
RalFinger/ral-fluff-qwen-image-lora · Hugging Face
Muapi/hero-run-effect-wan2.1-i2v-lora · Hugging Face
Muapi/flux-anime-blue-archive-style · Hugging Face
star-wars-jedi-outfit-flux-and-sd-1.5.safetensors · Muapi/star-wars ...
Skywork/Matrix-Game-2.0 · Hugging Face
Tongyi-MAI/Z-Image-Turbo · Hugging Face
InstantX/FLUX.1-dev-Controlnet-Union · Hugging Face
LiconStudio/Ltx2.3-VBVR-lora-I2V · Hugging Face
vLLM官方中文教程：用vllm实现所有的模型量化_51CTO博客_模型 量化
Qwen3.6-27B 本地私有化部署 + Claude Code 连接应用_qwen3.6 27b-CSDN博客
Qwen3 新一代原生多模态模型 Qwen3.5-27B 本地 vLLM 私有化部署，性能比肩 GPT-5-mini_vllm部署qwen3 ...
inference/kernel.py · deepseek-ai/DeepSeek-V4-Flash at main
