Revert jit-cache (shim pulls unavailable sm100a dep); restore working build

requirements.txt

@@ -1,23 +1,11 @@
-# FastVideo main @ the commit with FastH3 OmniRef PDD + NVFP4 consumer profiles
-# (hao-ai-lab/FastVideo#1907 and the rtx-pro-6000 profile) and the built-in
-# in-process UniprocExecutor (num_gpus==1). It pulls torch==2.12.0, gradio==5.32.0
-# and transformers>=5.15.0 as hard deps, so the Space SDK is pinned to 5.32.0.
-# cu130 wheels for Blackwell sm_120 (RTX PRO 6000 / ZeroGPU).
+# FastVideo main @ the FastH3 OmniRef PDD + NVFP4 consumer-profile commit, with
+# the in-process UniprocExecutor. Pulls torch==2.12.0, gradio==5.32.0,
+# transformers>=5.15.0. cu130 wheels for Blackwell sm_120 (RTX PRO 6000).
 --extra-index-url https://download.pytorch.org/whl/cu130
 fastvideo @ git+https://github.com/hao-ai-lab/FastVideo.git@376e445f0e8d192c2d9a5f28010a6b3a7012667e
 
 # NVFP4 FP4 GEMMs (packed linears + decoder) on Blackwell.
 flashinfer-python
-# Prebuilt flashinfer FP4 cubins for sm120 (RTX PRO 6000): skip the ~175 s
-# fp4_quantization_120f / fp4_gemm_cutlass_sm120 JIT compile on every cold boot
-# (the FastVideo analog of the official H3 Spaces' prebuilt-AOTI download).
-# Two packages: the shim (top-level `flashinfer_jit_cache` with __version__ and
-# provider discovery) + the sm120f provider (the actual cubins + entry point).
-# Installing the provider alone leaves a namespace package with no __version__.
---find-links https://flashinfer.ai/whl/cu130/flashinfer-jit-cache/
---find-links https://flashinfer.ai/whl/cu130/flashinfer-jit-cache-sm120f/
-flashinfer-jit-cache==0.7.2+cu130
-flashinfer-jit-cache-sm120f==0.7.2+cu130
 
 spaces
 pillow