Search results

Incorrect Results with FlexDecoding

Status: Open.

#233 In meta-pytorch/gpt-fast;

·zaptrem openedon Aug 19, 2025

mixtral-moe example fails to torch.compile

Status: Open.

#232 In meta-pytorch/gpt-fast;

·zou3519 openedon Jul 23, 2025

llama-3.1-8b sometimes giving weird results

Status: Open.

#230 In meta-pytorch/gpt-fast;

·zou3519 openedon Jul 23, 2025

Batteries included: promote some basic version/utils of reasonably fast offline/batched inference into PyTorch core (maybe based on gpt-fast, nano-vllm, torchao)

Status: Open.

#229 In meta-pytorch/gpt-fast;

·vadimkantorov openedon Jun 30, 2025

Error in TP: RuntimeError: get_group_info: no group info associated with the group name

Status: Open.

#228 In meta-pytorch/gpt-fast;

·zy-ning openedon Jun 9, 2025

Rotary Embeddings Implementation

Status: Open.

#226 In meta-pytorch/gpt-fast;

·hello-fri-end openedon Apr 9, 2025

Dynamo error when trying to run eval.py <code>'Tensor' object has no attribute 'mask_mod'</code>

Status: Open.

#223 In meta-pytorch/gpt-fast;

·bobrenjc93 openedon Mar 8, 2025

对于源码没有给出的模型（如DeepSeek-R1-Distill-Qwen-1.5B）该如何使用这个方法？

Status: Open.

#220 In meta-pytorch/gpt-fast;

·yabuke openedon Feb 11, 2025

AttributeError: 'Tensor' object has no attribute 'mask_mod'

Status: Open.

#219 In meta-pytorch/gpt-fast;

·jiapingW openedon Jan 15, 2025

Issue: Performance degradation with int8 quantization in multi-batch scenarios

Status: Open.

#218 In meta-pytorch/gpt-fast;

·kakarotzzz openedon Jan 14, 2025

int4 quant broken right now?

Status: Open.

#217 In meta-pytorch/gpt-fast;

·jerryzh168 openedon Dec 20, 2024

Llama 3.1 70B size mismatch for tok_embeddings.weight

Status: Open.

#215 In meta-pytorch/gpt-fast;

·albertbn openedon Dec 4, 2024