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). @ rc_054

AlpinDale 208cd5405f fix: cpu offloading with gptq		4 maanden geleden
..
compressed_tensors	4d4e767838 ci: take one of fixing lint issues	4 maanden geleden
gguf_utils	9d81716bfd [v0.5.3] Release Candidate (#388)	8 maanden geleden
utils	141672a0d4 kernels: disambiguate quantized types via a new ScalarType	4 maanden geleden
__init__.py	2b85ffb1a5 chore: minor cleanups	4 maanden geleden
aqlm.py	9be43994fe feat: fbgemm quantization support (#601)	5 maanden geleden
autoquant.py	9be43994fe feat: fbgemm quantization support (#601)	5 maanden geleden
awq.py	9be43994fe feat: fbgemm quantization support (#601)	5 maanden geleden
awq_marlin.py	141672a0d4 kernels: disambiguate quantized types via a new ScalarType	4 maanden geleden
base_config.py	0e6c400b13 feat: re-add GGUF (#600)	4 maanden geleden
bitsandbytes.py	d4c9fcd6e6 feat: support loading pre-quanted bnb checkpoints	4 maanden geleden
deepspeedfp.py	6b1fdd07bd chore: add isort and refactor formatting script and utils	4 maanden geleden
eetq.py	9be43994fe feat: fbgemm quantization support (#601)	5 maanden geleden
exl2.py	9be43994fe feat: fbgemm quantization support (#601)	5 maanden geleden
fbgemm_fp8.py	a20e2ce155 fix: pass cutlass_fp8_supported correctly for fbgemm_fp8	4 maanden geleden
fp8.py	4d4e767838 ci: take one of fixing lint issues	4 maanden geleden
gguf.py	4d4e767838 ci: take one of fixing lint issues	4 maanden geleden
gptq.py	208cd5405f fix: cpu offloading with gptq	4 maanden geleden
gptq_marlin.py	208cd5405f fix: cpu offloading with gptq	4 maanden geleden
gptq_marlin_24.py	141672a0d4 kernels: disambiguate quantized types via a new ScalarType	4 maanden geleden
hadamard.safetensors	9d81716bfd [v0.5.3] Release Candidate (#388)	8 maanden geleden
kv_cache.py	e81590d293 fix: `kv_cache_dtype=fp8` without scales for fp8 checkpoints	4 maanden geleden
marlin.py	9be43994fe feat: fbgemm quantization support (#601)	5 maanden geleden
qqq.py	e3f07b22c3 feat: support for QQQ W4A8 quantization (#612)	4 maanden geleden
quip.py	9be43994fe feat: fbgemm quantization support (#601)	5 maanden geleden
quip_utils.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 maanden geleden
schema.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 maanden geleden
squeezellm.py	9be43994fe feat: fbgemm quantization support (#601)	5 maanden geleden