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). @ 653d1a08d42e93e901390c5773791856088db279

AlpinDale 653d1a08d4 feat: add support for audio models (#891)		2 månader sedan
..
adapter_commons	2f61644f6e SPMD optimizations (#824)	3 månader sedan
assets	653d1a08d4 feat: add support for audio models (#891)	2 månader sedan
attention	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	2 månader sedan
common	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	2 månader sedan
distributed	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	2 månader sedan
endpoints	653d1a08d4 feat: add support for audio models (#891)	2 månader sedan
engine	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	2 månader sedan
executor	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	2 månader sedan
inputs	2f61644f6e SPMD optimizations (#824)	3 månader sedan
kv_quant	8a71788372 Add OLMoE (#772)	4 månader sedan
lora	369600855a xpu: disable punica kernels for XPU (#864)	3 månader sedan
modeling	653d1a08d4 feat: add support for audio models (#891)	2 månader sedan
multimodal	653d1a08d4 feat: add support for audio models (#891)	2 månader sedan
platforms	81c28d2a7f fix: use nvml to get consistent device names (#739)	5 månader sedan
plugins	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	2 månader sedan
processing	abfd4465ca feat: add support for chunked prefill + prefix caching (#871)	3 månader sedan
prompt_adapter	2f61644f6e SPMD optimizations (#824)	3 månader sedan
quantization	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	2 månader sedan
server	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	2 månader sedan
spec_decode	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	2 månader sedan
task_handler	22a4cd4595 core: fix spec decode metrics and envs circular import (#889)	2 månader sedan
transformers_utils	653d1a08d4 feat: add support for audio models (#891)	2 månader sedan
triton_utils	f1d0b77c92 [0.6.0] Release Candidate (#481)	6 månader sedan
__init__.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	6 månader sedan
_core_ext.py	9296d4b25d feat: dynamo support for ScalarType (#733)	5 månader sedan
_custom_ops.py	93bc863591 feat: Machete Kernels for Hopper GPUs (#842)	3 månader sedan
_ipex_ops.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	6 månader sedan
connections.py	c6c91edab7 ci: update & overhaul test units (#769)	3 månader sedan
constants.py	2f61644f6e SPMD optimizations (#824)	3 månader sedan
py.typed	1c988a48b2 fix logging and add py.typed	1 år sedan
scalar_type.py	f1d0b77c92 [0.6.0] Release Candidate (#481)	6 månader sedan
version.py	8b8d2ce7e2 ci: bump aphrodite version to 0.6.4.post1 (#859)	3 månader sedan