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). @ 561588d97d7cca90ed7fcdb936650046d0493c91

AlpinDale 04da8c33bd Revert "chore: use the `compressed-tensors` library to avoid code reuse (#704)" (#706)		4 hónapja
..
compressed_tensors	04da8c33bd Revert "chore: use the `compressed-tensors` library to avoid code reuse (#704)" (#706)	4 hónapja
gguf_utils	9d81716bfd [v0.5.3] Release Candidate (#388)	8 hónapja
utils	3170c0d4c6 fix: GPTQ/AWQ on Colab (#655)	4 hónapja
__init__.py	3f49a55f82 feat: add INT8 W8A16 quant for TPU (#663)	4 hónapja
aqlm.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 hónapja
autoquant.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 hónapja
awq.py	edec2e9a9e feat: migrate awq and awq_marlin to AphroditeParameter (#702)	4 hónapja
awq_marlin.py	edec2e9a9e feat: migrate awq and awq_marlin to AphroditeParameter (#702)	4 hónapja
base_config.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 hónapja
bitsandbytes.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 hónapja
deepspeedfp.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 hónapja
eetq.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 hónapja
exl2.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 hónapja
fbgemm_fp8.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 hónapja
fp8.py	4ec08af18b chore: update fused MoE weight loading (#700)	4 hónapja
gguf.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 hónapja
gptq.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 hónapja
gptq_marlin.py	4f6020cc86 chore: migrate gptq_marlin to AphroditeParameters (#699)	4 hónapja
gptq_marlin_24.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 hónapja
hadamard.safetensors	9d81716bfd [v0.5.3] Release Candidate (#388)	8 hónapja
kv_cache.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 hónapja
marlin.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 hónapja
qqq.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 hónapja
quip.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 hónapja
quip_utils.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 hónapja
schema.py	9d81716bfd [v0.5.3] Release Candidate (#388)	8 hónapja
squeezellm.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 hónapja
tpu_int8.py	3f49a55f82 feat: add INT8 W8A16 quant for TPU (#663)	4 hónapja