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). @ f5bbf07c9043cc381071174ecb6941dbd1c2a4f0

AlpinDale f5bbf07c90 chore: use the `compressed-tensors` library to avoid code reuse (#704)		hace 6 meses
..
compressed_tensors	f5bbf07c90 chore: use the `compressed-tensors` library to avoid code reuse (#704)	hace 6 meses
gguf_utils	9d81716bfd [v0.5.3] Release Candidate (#388)	hace 10 meses
utils	3170c0d4c6 fix: GPTQ/AWQ on Colab (#655)	hace 6 meses
__init__.py	3f49a55f82 feat: add INT8 W8A16 quant for TPU (#663)	hace 6 meses
aqlm.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	hace 6 meses
autoquant.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	hace 6 meses
awq.py	edec2e9a9e feat: migrate awq and awq_marlin to AphroditeParameter (#702)	hace 6 meses
awq_marlin.py	edec2e9a9e feat: migrate awq and awq_marlin to AphroditeParameter (#702)	hace 6 meses
base_config.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	hace 6 meses
bitsandbytes.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	hace 6 meses
deepspeedfp.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	hace 6 meses
eetq.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	hace 6 meses
exl2.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	hace 6 meses
fbgemm_fp8.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	hace 6 meses
fp8.py	4ec08af18b chore: update fused MoE weight loading (#700)	hace 6 meses
gguf.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	hace 6 meses
gptq.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	hace 6 meses
gptq_marlin.py	4f6020cc86 chore: migrate gptq_marlin to AphroditeParameters (#699)	hace 6 meses
gptq_marlin_24.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	hace 6 meses
hadamard.safetensors	9d81716bfd [v0.5.3] Release Candidate (#388)	hace 10 meses
kv_cache.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	hace 6 meses
marlin.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	hace 6 meses
qqq.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	hace 6 meses
quip.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	hace 6 meses
quip_utils.py	9d81716bfd [v0.5.3] Release Candidate (#388)	hace 10 meses
schema.py	9d81716bfd [v0.5.3] Release Candidate (#388)	hace 10 meses
squeezellm.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	hace 6 meses
tpu_int8.py	3f49a55f82 feat: add INT8 W8A16 quant for TPU (#663)	hace 6 meses