| .. |
|
adapter_commons
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
hace 4 meses |
|
attention
|
7a313483f1
chore: move update_flash_attn_metadata to attn backend (#731)
|
hace 3 meses |
|
common
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
hace 3 meses |
|
distributed
|
ef3a0f4cb1
fix: `custom_ar` check (#737)
|
hace 3 meses |
|
endpoints
|
9d9722b1c1
fix: metrics endpoint with RPC server (#747)
|
hace 3 meses |
|
engine
|
9d9722b1c1
fix: metrics endpoint with RPC server (#747)
|
hace 3 meses |
|
executor
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
hace 3 meses |
|
inputs
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
hace 3 meses |
|
kv_quant
|
e42a78381a
feat: switch from pylint to ruff (#322)
|
hace 10 meses |
|
lora
|
d9d85eeb6e
chore: register lora functions as torch ops (#732)
|
hace 3 meses |
|
modeling
|
acf2be3e44
chore: refactor llama3 rope
|
hace 3 meses |
|
multimodal
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
hace 3 meses |
|
platforms
|
81c28d2a7f
fix: use nvml to get consistent device names (#739)
|
hace 3 meses |
|
plugins
|
f76f2a5af0
feat: add aphrodite plugin system (#705)
|
hace 3 meses |
|
processing
|
577586309d
chore: multi-step args and sequence modifications (#713)
|
hace 3 meses |
|
prompt_adapter
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
hace 4 meses |
|
quantization
|
ccbda97416
fix: types in AQLM and GGUF for dynamo support (#736)
|
hace 3 meses |
|
server
|
ed9a6f97c1
fix: kill api server when pinging dead engine (#660)
|
hace 4 meses |
|
spec_decode
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
hace 3 meses |
|
task_handler
|
81c5f196eb
chore: various TPU fixes and optimizations (#746)
|
hace 3 meses |
|
transformers_utils
|
4648f16c84
chore: fix return statement in Detokenizer class (#727)
|
hace 3 meses |
|
triton_utils
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
hace 4 meses |
|
__init__.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
hace 4 meses |
|
_core_ext.py
|
9296d4b25d
feat: dynamo support for ScalarType (#733)
|
hace 3 meses |
|
_custom_ops.py
|
ccbda97416
fix: types in AQLM and GGUF for dynamo support (#736)
|
hace 3 meses |
|
_ipex_ops.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
hace 4 meses |
|
py.typed
|
1c988a48b2
fix logging and add py.typed
|
hace 1 año |
|
scalar_type.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
hace 4 meses |
|
version.py
|
c744443679
ci: bump to 0.6.1.post1 (#728)
|
hace 3 meses |
AlpinDale
acf2be3e44
chore: refactor llama3 rope