Try causal-conv1d 1.6.2 post1

Restore no-CCE FLA wrapper with transformers pin

Pin transformers and remove CCE

Pass FLA grouped constexpr args

Fix FLA grouped value-head backward patch

Make FLA backward patch contiguous

Install cut-cross-entropy and log CUDA memory

enable core scattermoe tilelang dflash fixes

add diagnostic tensor prefix breakdown

expose model diagnostics in gradio api

add model diagnostics endpoint

Deploy TorchAO FP8 ZeroGPU prototype

Install causal conv wheel and skip zero-advantage GRPO groups

Use torch cu130 and batch GRPO rollouts

Disable DeepGEMM on ZeroGPU FP8 path

Move FP8 model to CUDA inside ZeroGPU hot path

Install Qwen3.6 FP8 fast path dependencies