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). @ lm_head_lora

AlpinDale 80e7f3b0bd feat: support finetuned lm_head and embed_tokens in LoRA adapters		3 týždňov pred
..
adapter_commons	2f61644f6e SPMD optimizations (#824)	1 mesiac pred
assets	901900854e chore: consolidate environment variables within one file (#882)	4 týždňov pred
attention	901900854e chore: consolidate environment variables within one file (#882)	4 týždňov pred
common	80e7f3b0bd feat: support finetuned lm_head and embed_tokens in LoRA adapters	3 týždňov pred
distributed	901900854e chore: consolidate environment variables within one file (#882)	4 týždňov pred
endpoints	901900854e chore: consolidate environment variables within one file (#882)	4 týždňov pred
engine	80e7f3b0bd feat: support finetuned lm_head and embed_tokens in LoRA adapters	3 týždňov pred
executor	901900854e chore: consolidate environment variables within one file (#882)	4 týždňov pred
inputs	2f61644f6e SPMD optimizations (#824)	1 mesiac pred
kv_quant	8a71788372 Add OLMoE (#772)	2 mesiacov pred
lora	80e7f3b0bd feat: support finetuned lm_head and embed_tokens in LoRA adapters	3 týždňov pred
modeling	80e7f3b0bd feat: support finetuned lm_head and embed_tokens in LoRA adapters	3 týždňov pred
multimodal	901900854e chore: consolidate environment variables within one file (#882)	4 týždňov pred
platforms	81c28d2a7f fix: use nvml to get consistent device names (#739)	3 mesiacov pred
plugins	901900854e chore: consolidate environment variables within one file (#882)	4 týždňov pred
processing	abfd4465ca feat: add support for chunked prefill + prefix caching (#871)	1 mesiac pred
prompt_adapter	2f61644f6e SPMD optimizations (#824)	1 mesiac pred
quantization	901900854e chore: consolidate environment variables within one file (#882)	4 týždňov pred
server	901900854e chore: consolidate environment variables within one file (#882)	4 týždňov pred
spec_decode	1405051912 attention: add `AttentionState` abstraction (#863)	1 mesiac pred
task_handler	901900854e chore: consolidate environment variables within one file (#882)	4 týždňov pred
transformers_utils	901900854e chore: consolidate environment variables within one file (#882)	4 týždňov pred
triton_utils	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
__init__.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
_core_ext.py	9296d4b25d feat: dynamo support for ScalarType (#733)	3 mesiacov pred
_custom_ops.py	93bc863591 feat: Machete Kernels for Hopper GPUs (#842)	1 mesiac pred
_ipex_ops.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
connections.py	c6c91edab7 ci: update & overhaul test units (#769)	1 mesiac pred
constants.py	2f61644f6e SPMD optimizations (#824)	1 mesiac pred
envs.py	901900854e chore: consolidate environment variables within one file (#882)	4 týždňov pred
py.typed	1c988a48b2 fix logging and add py.typed	1 rok pred
scalar_type.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
version.py	8b8d2ce7e2 ci: bump aphrodite version to 0.6.4.post1 (#859)	1 mesiac pred