AlpinDale fc5ef786b0 Merge branch 'main' into lm_head_lora 6 dní pred
..
adapter_commons 2f61644f6e SPMD optimizations (#824) 2 mesiacov pred
assets a5bfc2bc3d VLM: add support for LLaVA-Onevision model (#1100) 1 týždeň pred
attention 7fffa507ff build: build flash attention kernels inside aphrodite (#1085) 1 týždeň pred
common fc5ef786b0 Merge branch 'main' into lm_head_lora 6 dní pred
compilation 960dee2f97 torch.compile: fix functionalization (#1045) 1 mesiac pred
distributed 76088aa43a distributed: allow IPv6 in APHRODITE_HOST_IP with ZMQ (#1105) 1 týždeň pred
endpoints f20f5c3491 samplers: improved DRY performance (#1108) 1 týždeň pred
engine fc5ef786b0 Merge branch 'main' into lm_head_lora 6 dní pred
executor 6212072245 api: support LoRA lineage and base model metadata management (#1072) 1 mesiac pred
inputs cc5e185795 VLM: support passing multimodal processor kwargs (#1102) 1 týždeň pred
kv_quant 8a71788372 Add OLMoE (#772) 3 mesiacov pred
lora fc5ef786b0 Merge branch 'main' into lm_head_lora 6 dní pred
modeling fc5ef786b0 Merge branch 'main' into lm_head_lora 6 dní pred
multimodal cc5e185795 VLM: support passing multimodal processor kwargs (#1102) 1 týždeň pred
platforms f2b6dc3872 cpu: add support for W8A8 quantization via compressed-tensor (#1017) 1 mesiac pred
plugins 9797d38b24 torch.compile: allow adding custom compile backends via plugins (#1041) 1 mesiac pred
processing f561a54a43 core: fix async postprocessor in case of preemption (#1000) 1 mesiac pred
prompt_adapter 30d02d0747 chore: remove peft as a requirement (#1006) 1 mesiac pred
quantization ed63c079f7 Triton: remove atomic add op from awq triton (#1094) 1 týždeň pred
server 9a7d5514c4 feat: introduce MQAphroditeEngine (#1056) 1 mesiac pred
spec_decode a0f0160b79 spec decode: remove dead code from draft bonus tokens (#1101) 1 týždeň pred
transformers_utils cc5e185795 VLM: support passing multimodal processor kwargs (#1102) 1 týždeň pred
triton_utils 4593a3b306 chore: remove dead code from triton sampling kernels (#1049) 1 mesiac pred
worker d44da0332c misc: rename `CudaMemoryProfiler` to `DeviceMemoryProfiler` (#1099) 1 týždeň pred
__init__.py f1d0b77c92 [0.6.0] Release Candidate (#481) 5 mesiacov pred
_core_ext.py f1ea7711bd core: do not compile ScalarType for torch < 2.4.0 (#938) 1 mesiac pred
_custom_ops.py 7fffa507ff build: build flash attention kernels inside aphrodite (#1085) 1 týždeň pred
_ipex_ops.py 6951928522 xpu: bump IPEX to 2.3, support GQA (#1042) 1 mesiac pred
connections.py c6c91edab7 ci: update & overhaul test units (#769) 2 mesiacov pred
constants.py 2f61644f6e SPMD optimizations (#824) 2 mesiacov pred
py.typed 1c988a48b2 fix logging and add py.typed 1 rok pred
scalar_type.py f1d0b77c92 [0.6.0] Release Candidate (#481) 5 mesiacov pred
version.py cbd51a208a ci: bump to 0.6.5 (#964) 1 mesiac pred