| .. |
|
adapter_commons
|
2f61644f6e
SPMD optimizations (#824)
|
il y a 2 mois |
|
assets
|
a5bfc2bc3d
VLM: add support for LLaVA-Onevision model (#1100)
|
il y a 2 semaines |
|
attention
|
7fffa507ff
build: build flash attention kernels inside aphrodite (#1085)
|
il y a 2 semaines |
|
common
|
172dee2573
(2/N) Triton Backend: integrate Triton activation kernels (#1126)
|
il y a 3 jours |
|
compilation
|
960dee2f97
torch.compile: fix functionalization (#1045)
|
il y a 1 mois |
|
distributed
|
76088aa43a
distributed: allow IPv6 in APHRODITE_HOST_IP with ZMQ (#1105)
|
il y a 2 semaines |
|
endpoints
|
3e6addcc2c
LLM: enable batched inference for llm.chat() API (#1120)
|
il y a 5 jours |
|
engine
|
5b03d67abb
Core: add output streaming support to multi-step + async (#1112)
|
il y a 2 semaines |
|
executor
|
6212072245
api: support LoRA lineage and base model metadata management (#1072)
|
il y a 1 mois |
|
inputs
|
cc5e185795
VLM: support passing multimodal processor kwargs (#1102)
|
il y a 2 semaines |
|
kv_quant
|
8a71788372
Add OLMoE (#772)
|
il y a 4 mois |
|
lora
|
6d8df254c7
LoRA: skip loading unsupported weight modules (#1109)
|
il y a 2 semaines |
|
modeling
|
172dee2573
(2/N) Triton Backend: integrate Triton activation kernels (#1126)
|
il y a 3 jours |
|
multimodal
|
cc5e185795
VLM: support passing multimodal processor kwargs (#1102)
|
il y a 2 semaines |
|
platforms
|
f2b6dc3872
cpu: add support for W8A8 quantization via compressed-tensor (#1017)
|
il y a 1 mois |
|
plugins
|
9797d38b24
torch.compile: allow adding custom compile backends via plugins (#1041)
|
il y a 1 mois |
|
processing
|
f561a54a43
core: fix async postprocessor in case of preemption (#1000)
|
il y a 1 mois |
|
prompt_adapter
|
30d02d0747
chore: remove peft as a requirement (#1006)
|
il y a 1 mois |
|
quantization
|
349a612338
chore: bump bitsandbytes version to latest; enable cuda graphs for 4bit bnb (#1123)
|
il y a 5 jours |
|
server
|
9a7d5514c4
feat: introduce MQAphroditeEngine (#1056)
|
il y a 1 mois |
|
spec_decode
|
a0f0160b79
spec decode: remove dead code from draft bonus tokens (#1101)
|
il y a 2 semaines |
|
transformers_utils
|
cc5e185795
VLM: support passing multimodal processor kwargs (#1102)
|
il y a 2 semaines |
|
triton_utils
|
4593a3b306
chore: remove dead code from triton sampling kernels (#1049)
|
il y a 1 mois |
|
worker
|
2cd6ef2d5a
misc: skip dumping inputs when unpicklable
|
il y a 2 semaines |
|
__init__.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
il y a 5 mois |
|
_core_ext.py
|
f1ea7711bd
core: do not compile ScalarType for torch < 2.4.0 (#938)
|
il y a 1 mois |
|
_custom_ops.py
|
fa84f8102e
kernels: split marlin kernels for faster compile, fix MoE, temporarily remove HQQ (#1119)
|
il y a 5 jours |
|
_ipex_ops.py
|
6951928522
xpu: bump IPEX to 2.3, support GQA (#1042)
|
il y a 1 mois |
|
connections.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
il y a 2 mois |
|
constants.py
|
2f61644f6e
SPMD optimizations (#824)
|
il y a 2 mois |
|
py.typed
|
1c988a48b2
fix logging and add py.typed
|
il y a 1 an |
|
scalar_type.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
il y a 5 mois |
|
version.py
|
b20c4570d2
CI: bump aphrodite-engine to v0.6.6 (#1111)
|
il y a 2 semaines |
AlpinDale
172dee2573
(2/N) Triton Backend: integrate Triton activation kernels (#1126)