| .. |
|
__init__.py
|
07aa2a492f
upstream: add option to specify tokenizer
|
hai 1 ano |
|
block.py
|
b5694be865
chore: use a pool to reuse LogicalTokenBlock.token_ids
|
hai 7 meses |
|
config.py
|
0613d91551
fix: kv head calculation with MPT GQA
|
hai 7 meses |
|
grammar.py
|
0527131e93
fix: grammar logits processor (#268)
|
hai 1 ano |
|
inputs.py
|
8004c9f782
fix: import for multimodaldata
|
hai 7 meses |
|
logger.py
|
46159b107a
formatting: pt1
|
hai 8 meses |
|
logits_processor.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
hai 10 meses |
|
outputs.py
|
90ceab32ff
refactor: consolidate prompt args to LLM engines
|
hai 7 meses |
|
pooling_params.py
|
be8154a8a0
feat: proper embeddings API with e5-mistral-7b support
|
hai 8 meses |
|
sampling_params.py
|
e8b7f53321
allow prompt token IDs in the logits processor api
|
hai 8 meses |
|
sequence.py
|
8d77c69cbd
feat: support image processor and add llava example
|
hai 7 meses |
|
test_utils.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
hai 10 meses |
|
utils.py
|
6a57861fca
feat: initial XPU support via intel_extension_for_pytorch (#571)
|
hai 7 meses |
AlpinDale
0613d91551
fix: kv head calculation with MPT GQA