.. |
__init__.py
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
hai 8 meses |
batch_expansion.py
|
16b587c104
fix: hidden states handling in batch expansion for spec decoding (#839)
|
hai 1 mes |
draft_model_runner.py
|
1405051912
attention: add `AttentionState` abstraction (#863)
|
hai 1 mes |
interfaces.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
hai 4 meses |
medusa_worker.py
|
2f61644f6e
SPMD optimizations (#824)
|
hai 1 mes |
metrics.py
|
2f61644f6e
SPMD optimizations (#824)
|
hai 1 mes |
mlp_speculator_worker.py
|
2f61644f6e
SPMD optimizations (#824)
|
hai 1 mes |
multi_step_worker.py
|
1394008421
chore: decouple `should_modify_greedy_probs_inplace (#671)
|
hai 4 meses |
ngram_worker.py
|
2f61644f6e
SPMD optimizations (#824)
|
hai 1 mes |
proposer_worker_base.py
|
2f61644f6e
SPMD optimizations (#824)
|
hai 1 mes |
smaller_tp_proposer_worker.py
|
2f61644f6e
SPMD optimizations (#824)
|
hai 1 mes |
spec_decode_worker.py
|
16b587c104
fix: hidden states handling in batch expansion for spec decoding (#839)
|
hai 1 mes |
target_model_runner.py
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
hai 3 meses |
top1_proposer.py
|
16b587c104
fix: hidden states handling in batch expansion for spec decoding (#839)
|
hai 1 mes |
util.py
|
16b587c104
fix: hidden states handling in batch expansion for spec decoding (#839)
|
hai 1 mes |