.. |
adapter_commons
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 månader sedan |
assets
|
c6c91edab7
ci: update & overhaul test units (#769)
|
1 månad sedan |
attention
|
7a313483f1
chore: move update_flash_attn_metadata to attn backend (#731)
|
3 månader sedan |
common
|
c6c91edab7
ci: update & overhaul test units (#769)
|
1 månad sedan |
distributed
|
0f1af04cf5
frontend: minor logging improvements (#787)
|
2 månader sedan |
endpoints
|
c6c91edab7
ci: update & overhaul test units (#769)
|
1 månad sedan |
engine
|
f088ea81c7
fix: --max-seq-len-to-capture arg (#818)
|
1 månad sedan |
executor
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
3 månader sedan |
inputs
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
3 månader sedan |
kv_quant
|
8a71788372
Add OLMoE (#772)
|
2 månader sedan |
lora
|
d9d85eeb6e
chore: register lora functions as torch ops (#732)
|
3 månader sedan |
modeling
|
273c61d406
guard against nan temperature from dynatemp (or anywhere else).
|
1 månad sedan |
multimodal
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
3 månader sedan |
platforms
|
81c28d2a7f
fix: use nvml to get consistent device names (#739)
|
3 månader sedan |
plugins
|
f76f2a5af0
feat: add aphrodite plugin system (#705)
|
4 månader sedan |
processing
|
577586309d
chore: multi-step args and sequence modifications (#713)
|
3 månader sedan |
prompt_adapter
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 månader sedan |
quantization
|
f98e7b2f8c
feat: add HQQ quantization support (#795)
|
2 månader sedan |
server
|
0256ed236b
feat: windows support (#790)
|
2 månader sedan |
spec_decode
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
3 månader sedan |
task_handler
|
0f1af04cf5
frontend: minor logging improvements (#787)
|
2 månader sedan |
transformers_utils
|
fb96041ae3
fix: demote skip_special_tokens assertion to logger error (#778)
|
2 månader sedan |
triton_utils
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 månader sedan |
__init__.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 månader sedan |
_core_ext.py
|
9296d4b25d
feat: dynamo support for ScalarType (#733)
|
3 månader sedan |
_custom_ops.py
|
f98e7b2f8c
feat: add HQQ quantization support (#795)
|
2 månader sedan |
_ipex_ops.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 månader sedan |
connections.py
|
c6c91edab7
ci: update & overhaul test units (#769)
|
1 månad sedan |
py.typed
|
1c988a48b2
fix logging and add py.typed
|
1 år sedan |
scalar_type.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 månader sedan |
version.py
|
f0e00f1b43
ci: bump to 0.6.3.post1 (#801)
|
2 månader sedan |