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