LZY-the-boys/lm-evaluation-harness-fast
speedup for lm-evaluation-harness; support tensor-parallel inference and data-parallel inference; support gptq, bitsandbytes, peft and exllamav2.
PythonMIT
speedup for lm-evaluation-harness; support tensor-parallel inference and data-parallel inference; support gptq, bitsandbytes, peft and exllamav2.
PythonMIT