Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

fraQtl
/
fraqtl-sm80-runtime

kv-cache
kv-cache-compression
vllm
a100
fraqtl
Model card Files Files and versions
xet
Community
fraqtl-sm80-runtime
247 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 11 commits
samuel-salfati's picture
samuel-salfati
Fix tilde strikethrough rendering (~ -> โ‰ˆ)
87bbc79 verified 2 days ago
  • .gitattributes
    1.6 kB
    Option-B repro kit: prebuilt SM80 binary wheel (no CUDA/calibration source, audited), build receipt, repro script, license 7 days ago
  • LICENSE
    700 Bytes
    Option-B repro kit: prebuilt SM80 binary wheel (no CUDA/calibration source, audited), build receipt, repro script, license 7 days ago
  • README.md
    2.71 kB
    Fix tilde strikethrough rendering (~ -> โ‰ˆ) 2 days ago
  • fraqtl_repro_receipts.py
    17.9 kB
    Two-model repro: --model flag, qwen3 8/32/128K support 2 days ago
  • fraqtl_runtime-0.2.0+sm80-py3-none-any.whl
    247 MB
    xet
    integrations/ as source for torch.compile parity (kernel binary + calibration exclusion unchanged); script drops profiler override 6 days ago
  • wheel_build_receipt.json
    3.34 kB
    Rebuild with qwen3 qk-norm adapter fix + mixed-step routing fix (batch>=2 needle-drop, 2026-07-03 root cause) 3 days ago