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). @ c1c37c755d5df53397610c6e7fc316db0898cd15

AlpinDale 4d4e767838 ci: take one of fixing lint issues		4 ماه پیش
..
__init__.py	6b1fdd07bd chore: add isort and refactor formatting script and utils	4 ماه پیش
arctic.py	0f4a9ee77b quantized lm_head (#582)	4 ماه پیش
baichuan.py	0f4a9ee77b quantized lm_head (#582)	4 ماه پیش
blip.py	9f010deb8a feat: add blip-2 support	4 ماه پیش
blip2.py	9f010deb8a feat: add blip-2 support	4 ماه پیش
bloom.py	4d4e767838 ci: take one of fixing lint issues	4 ماه پیش
chameleon.py	c9310eeb02 fix: skip loading lm_head for tie_word_embeddings models	4 ماه پیش
chatglm.py	0f4a9ee77b quantized lm_head (#582)	4 ماه پیش
clip.py	e26a4ac698 chore: avoid loading the unused layers and init the VLM up to the required feature space	4 ماه پیش
commandr.py	0f4a9ee77b quantized lm_head (#582)	4 ماه پیش
dbrx.py	0f4a9ee77b quantized lm_head (#582)	4 ماه پیش
decilm.py	56e0b8223c chore: add base class for LoRA-supported models	5 ماه پیش
deepseek.py	0f4a9ee77b quantized lm_head (#582)	4 ماه پیش
deepseek_v2.py	1efd0f89b7 feat: support FP8 for DeepSeekV2 MoE	4 ماه پیش
falcon.py	4d4e767838 ci: take one of fixing lint issues	4 ماه پیش
fuyu.py	9e9515f39a fix: feature size calculation for Llava-next	4 ماه پیش
gemma.py	4d4e767838 ci: take one of fixing lint issues	4 ماه پیش
gemma2.py	4d4e767838 ci: take one of fixing lint issues	4 ماه پیش
gpt2.py	4d4e767838 ci: take one of fixing lint issues	4 ماه پیش
gpt_bigcode.py	4d4e767838 ci: take one of fixing lint issues	4 ماه پیش
gpt_j.py	0f4a9ee77b quantized lm_head (#582)	4 ماه پیش
gpt_neox.py	0f4a9ee77b quantized lm_head (#582)	4 ماه پیش
idefics2_vision_model.py	9a50e3b4eb refactor: minicpmv and port Idefix2VisionTransformer	4 ماه پیش
interfaces.py	e76bbe72eb chore: handle aborted requests for jamba	4 ماه پیش
intern_vit.py	92987963a4 fix: RMSNorm forward in InternViT attention qk_layernorm	4 ماه پیش
internlm2.py	9cf1275f03 feat: add internvl support	4 ماه پیش
internvl.py	9e9515f39a fix: feature size calculation for Llava-next	4 ماه پیش
jais.py	4d4e767838 ci: take one of fixing lint issues	4 ماه پیش
jamba.py	f83eb07fd1 feat: use FusedMoE for jamba	4 ماه پیش
llama.py	4d4e767838 ci: take one of fixing lint issues	4 ماه پیش
llama_embedding.py	50b7c13db0 refactor: attention selector (#552)	5 ماه پیش
llava.py	acbdc50a71 fix: `vocab_size` field access in llava	4 ماه پیش
llava_next.py	9e9515f39a fix: feature size calculation for Llava-next	4 ماه پیش
medusa.py	d9f4c36edd feat: Medusa speculative decoding support (#590)	4 ماه پیش
minicpm.py	c9310eeb02 fix: skip loading lm_head for tie_word_embeddings models	4 ماه پیش
minicpmv.py	9a50e3b4eb refactor: minicpmv and port Idefix2VisionTransformer	4 ماه پیش
mixtral.py	00503b9fc1 feat: non-uniform quantization via `compressed-tensors` for llama	4 ماه پیش
mixtral_quant.py	0f4a9ee77b quantized lm_head (#582)	4 ماه پیش
mlp_speculator.py	db73f03cdc fix: use ParallelLMHead for MLPSpeculator	4 ماه پیش
mpt.py	4d4e767838 ci: take one of fixing lint issues	4 ماه پیش
na_vit.py	9a50e3b4eb refactor: minicpmv and port Idefix2VisionTransformer	4 ماه پیش
nemotron.py	18b45266bb feat: add nemotron HF support (#606)	4 ماه پیش
olmo.py	c9310eeb02 fix: skip loading lm_head for tie_word_embeddings models	4 ماه پیش
opt.py	4d4e767838 ci: take one of fixing lint issues	4 ماه پیش
orion.py	0f4a9ee77b quantized lm_head (#582)	4 ماه پیش
paligemma.py	c3ee71a437 feat: port SiglipVisionModel from transformers	4 ماه پیش
persimmon.py	e13a66925c feat: add fuyu vision model and persimmon language model support	4 ماه پیش
phi.py	0f4a9ee77b quantized lm_head (#582)	4 ماه پیش
phi3_small.py	0f4a9ee77b quantized lm_head (#582)	4 ماه پیش
phi3v.py	9e9515f39a fix: feature size calculation for Llava-next	4 ماه پیش
qwen.py	0f4a9ee77b quantized lm_head (#582)	4 ماه پیش
qwen2.py	d357341203 chore: add pipeline parallel support for Qwen	4 ماه پیش
qwen2_moe.py	d357341203 chore: add pipeline parallel support for Qwen	4 ماه پیش
siglip.py	4d4e767838 ci: take one of fixing lint issues	4 ماه پیش
stablelm.py	0f4a9ee77b quantized lm_head (#582)	4 ماه پیش
starcoder2.py	0f4a9ee77b quantized lm_head (#582)	4 ماه پیش
utils.py	165a3aa7b3 fix: fp8 marlin and cpu offloading with fp8 marlin	4 ماه پیش
xverse.py	0f4a9ee77b quantized lm_head (#582)	4 ماه پیش