.. |
adapter_commons
|
99680b2d23
feat: soft prompts (#589)
|
4 months ago |
attention
|
fa15bad2ea
chore: minor AMD fixes
|
4 months ago |
common
|
ed6717d0c0
feat: initial support for control vectors
|
4 months ago |
control_vectors
|
ed6717d0c0
feat: initial support for control vectors
|
4 months ago |
distributed
|
f91991f584
fix: f-string fixes
|
4 months ago |
endpoints
|
ed6717d0c0
feat: initial support for control vectors
|
4 months ago |
engine
|
ed6717d0c0
feat: initial support for control vectors
|
4 months ago |
executor
|
ed6717d0c0
feat: initial support for control vectors
|
4 months ago |
inputs
|
4f7d212b70
feat: remove vision language config
|
4 months ago |
kv_quant
|
e42a78381a
feat: switch from pylint to ruff (#322)
|
9 months ago |
lora
|
f91991f584
fix: f-string fixes
|
4 months ago |
modeling
|
acbdc50a71
fix: `vocab_size` field access in llava
|
4 months ago |
multimodal
|
f91991f584
fix: f-string fixes
|
4 months ago |
platforms
|
a3e26391e4
chore: add a wrapper for torch.inference_mode decorator
|
4 months ago |
processing
|
ed6717d0c0
feat: initial support for control vectors
|
4 months ago |
prompt_adapter
|
f91991f584
fix: f-string fixes
|
4 months ago |
quantization
|
ba371fbbbd
feat: AWQ marlin kernels (#603)
|
4 months ago |
spec_decode
|
a4cbcfe59f
feat: disable logprob serialization to CPU for spec decode
|
4 months ago |
task_handler
|
f91991f584
fix: f-string fixes
|
4 months ago |
transformers_utils
|
45a004874c
chore: allow specifying custom Executor
|
4 months ago |
triton_utils
|
c8d398a4ae
feat: add custom triton cache manager
|
4 months ago |
__init__.py
|
0c17c2a8a7
chore: add commit hash, clean up engine logs
|
4 months ago |
_custom_ops.py
|
ba371fbbbd
feat: AWQ marlin kernels (#603)
|
4 months ago |
_ipex_ops.py
|
9d7beaa5b9
chore: separate kv_scale into k_scale and v_scale
|
4 months ago |
py.typed
|
1c988a48b2
fix logging and add py.typed
|
1 year ago |
version.py
|
9038dea2df
fix: short commit hash import error
|
4 months ago |