.. |
adapter_commons
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 months ago |
attention
|
7a313483f1
chore: move update_flash_attn_metadata to attn backend (#731)
|
3 months ago |
common
|
73177656ed
feat: quant_llm support (#755)
|
3 months ago |
distributed
|
ef3a0f4cb1
fix: `custom_ar` check (#737)
|
3 months ago |
endpoints
|
a604ab69c4
fix: kobold api for horde (#763)
|
3 months ago |
engine
|
73177656ed
feat: quant_llm support (#755)
|
3 months ago |
executor
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
3 months ago |
inputs
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
3 months ago |
kv_quant
|
e42a78381a
feat: switch from pylint to ruff (#322)
|
9 months ago |
lora
|
d9d85eeb6e
chore: register lora functions as torch ops (#732)
|
3 months ago |
modeling
|
2b7cd1d4ec
wip
|
3 months ago |
multimodal
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
3 months ago |
platforms
|
81c28d2a7f
fix: use nvml to get consistent device names (#739)
|
3 months ago |
plugins
|
f76f2a5af0
feat: add aphrodite plugin system (#705)
|
3 months ago |
processing
|
577586309d
chore: multi-step args and sequence modifications (#713)
|
3 months ago |
prompt_adapter
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 months ago |
quantization
|
2b7cd1d4ec
wip
|
3 months ago |
server
|
ed9a6f97c1
fix: kill api server when pinging dead engine (#660)
|
4 months ago |
spec_decode
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
3 months ago |
task_handler
|
81c5f196eb
chore: various TPU fixes and optimizations (#746)
|
3 months ago |
transformers_utils
|
4648f16c84
chore: fix return statement in Detokenizer class (#727)
|
3 months ago |
triton_utils
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 months ago |
__init__.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 months ago |
_core_ext.py
|
9296d4b25d
feat: dynamo support for ScalarType (#733)
|
3 months ago |
_custom_ops.py
|
2b7cd1d4ec
wip
|
3 months ago |
_ipex_ops.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 months ago |
py.typed
|
1c988a48b2
fix logging and add py.typed
|
1 year ago |
scalar_type.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 months ago |
version.py
|
0e0bd02b52
ci: bump version to 0.6.2 (#758)
|
3 months ago |