| .. |
|
adapter_commons
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
vor 4 Monaten |
|
attention
|
7a313483f1
chore: move update_flash_attn_metadata to attn backend (#731)
|
vor 3 Monaten |
|
common
|
63793602d6
fix: prefix caching conditional
|
vor 2 Monaten |
|
distributed
|
064c701d18
formatting
|
vor 2 Monaten |
|
endpoints
|
064c701d18
formatting
|
vor 2 Monaten |
|
engine
|
5f75490026
fix: add some triton guards
|
vor 2 Monaten |
|
executor
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
vor 3 Monaten |
|
inputs
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
vor 3 Monaten |
|
kv_quant
|
8a71788372
Add OLMoE (#772)
|
vor 2 Monaten |
|
lora
|
d9d85eeb6e
chore: register lora functions as torch ops (#732)
|
vor 3 Monaten |
|
modeling
|
4495b7ab63
formatting
|
vor 2 Monaten |
|
multimodal
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
vor 3 Monaten |
|
platforms
|
81c28d2a7f
fix: use nvml to get consistent device names (#739)
|
vor 3 Monaten |
|
plugins
|
f76f2a5af0
feat: add aphrodite plugin system (#705)
|
vor 4 Monaten |
|
processing
|
577586309d
chore: multi-step args and sequence modifications (#713)
|
vor 3 Monaten |
|
prompt_adapter
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
vor 4 Monaten |
|
quantization
|
eee3cf5dab
fix: make AMD usable (#775)
|
vor 2 Monaten |
|
server
|
064c701d18
formatting
|
vor 2 Monaten |
|
spec_decode
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
vor 3 Monaten |
|
task_handler
|
81c5f196eb
chore: various TPU fixes and optimizations (#746)
|
vor 3 Monaten |
|
transformers_utils
|
fb96041ae3
fix: demote skip_special_tokens assertion to logger error (#778)
|
vor 2 Monaten |
|
triton_utils
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
vor 4 Monaten |
|
__init__.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
vor 4 Monaten |
|
_core_ext.py
|
9296d4b25d
feat: dynamo support for ScalarType (#733)
|
vor 3 Monaten |
|
_custom_ops.py
|
73177656ed
feat: quant_llm support (#755)
|
vor 3 Monaten |
|
_ipex_ops.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
vor 4 Monaten |
|
py.typed
|
1c988a48b2
fix logging and add py.typed
|
vor 1 Jahr |
|
scalar_type.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
vor 4 Monaten |
|
version.py
|
4d3d819507
ci: bump version to 0.6.2.post1 (#779)
|
vor 2 Monaten |
AlpinDale
4495b7ab63
formatting