david/aphrodite-engine: PygmalionAI's large-scale inference engine pygmalion.chat It is designed to serve as the inference endpoint for the PygmalionAI website, and to allow serving the Pygmalion models to a large number of users with blazing fast speeds (thanks to vLLM's Paged Attention). @ control-vectors

AlpinDale ba371fbbbd feat: AWQ marlin kernels (#603)		пре 4 месеци
..
aqlm	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	пре 5 месеци
autoquant	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	пре 5 месеци
awq	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	пре 5 месеци
compressed_tensors	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	пре 5 месеци
cutlass_w8a8	e7e847c3df fix: turn off cutlass scaled_mm for ada lovelace cards	пре 4 месеци
exl2	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	пре 5 месеци
fp8	ba371fbbbd feat: AWQ marlin kernels (#603)	пре 4 месеци
gguf	9d81716bfd [v0.5.3] Release Candidate (#388)	пре 8 месеци
gptq	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	пре 5 месеци
gptq_marlin	ba371fbbbd feat: AWQ marlin kernels (#603)	пре 4 месеци
int8_kvcache	9810daa699 feat: INT8 KV Cache (#298)	пре 10 месеци
marlin	ba371fbbbd feat: AWQ marlin kernels (#603)	пре 4 месеци
quip	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	пре 5 месеци
squeezellm	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	пре 5 месеци
quant_ops.h	ba371fbbbd feat: AWQ marlin kernels (#603)	пре 4 месеци