| .. |
|
__init__.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
il y a 10 mois |
|
batch_expansion.py
|
af43576da0
feat: add MLPSpeculator speculative decoding support (#572)
|
il y a 7 mois |
|
draft_model_runner.py
|
99680b2d23
feat: soft prompts (#589)
|
il y a 6 mois |
|
interfaces.py
|
16dff9babc
chore: enable bonus token in spec decoding for KV cache based models
|
il y a 6 mois |
|
medusa_worker.py
|
16dff9babc
chore: enable bonus token in spec decoding for KV cache based models
|
il y a 6 mois |
|
metrics.py
|
7253e9052d
feat: integrate typical acceptance sampling for spec decoding
|
il y a 7 mois |
|
mlp_speculator_worker.py
|
16dff9babc
chore: enable bonus token in spec decoding for KV cache based models
|
il y a 6 mois |
|
multi_step_worker.py
|
16dff9babc
chore: enable bonus token in spec decoding for KV cache based models
|
il y a 6 mois |
|
ngram_worker.py
|
16dff9babc
chore: enable bonus token in spec decoding for KV cache based models
|
il y a 6 mois |
|
proposer_worker_base.py
|
16dff9babc
chore: enable bonus token in spec decoding for KV cache based models
|
il y a 6 mois |
|
smaller_tp_proposer_worker.py
|
16dff9babc
chore: enable bonus token in spec decoding for KV cache based models
|
il y a 6 mois |
|
spec_decode_worker.py
|
16dff9babc
chore: enable bonus token in spec decoding for KV cache based models
|
il y a 6 mois |
|
top1_proposer.py
|
16dff9babc
chore: enable bonus token in spec decoding for KV cache based models
|
il y a 6 mois |
|
util.py
|
af43576da0
feat: add MLPSpeculator speculative decoding support (#572)
|
il y a 7 mois |
AlpinDale
16dff9babc
chore: enable bonus token in spec decoding for KV cache based models