| .. |
|
__init__.py
|
07aa2a492f
upstream: add option to specify tokenizer
|
1 anno fa |
|
block.py
|
7df7b8ca53
optimization: reduce end-to-end overhead from python obj allocation (#666)
|
6 mesi fa |
|
config.py
|
92cee435e2
rocm: add more quants, fix _scaled_mm call (#1062)
|
2 mesi fa |
|
connections.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
6 mesi fa |
|
envs.py
|
9a7d5514c4
feat: introduce MQAphroditeEngine (#1056)
|
2 mesi fa |
|
grammar.py
|
8a71788372
Add OLMoE (#772)
|
4 mesi fa |
|
logger.py
|
22a4cd4595
core: fix spec decode metrics and envs circular import (#889)
|
2 mesi fa |
|
logits_processor.py
|
8a71788372
Add OLMoE (#772)
|
4 mesi fa |
|
outputs.py
|
055c8905a3
api: add sampling/engine option to return only deltas or final output (#1035)
|
2 mesi fa |
|
pooling_params.py
|
2f61644f6e
SPMD optimizations (#824)
|
3 mesi fa |
|
sampling_params.py
|
814c850d89
fix: validate `n` in the sampling params (#1075)
|
2 mesi fa |
|
sequence.py
|
651678d2df
VLM: use `SequenceData.from_token_counts` to create dummy data (#1093)
|
1 mese fa |
|
test_utils.py
|
8a71788372
Add OLMoE (#772)
|
4 mesi fa |
|
utils.py
|
9bdf8d5bfa
mamba: enable continuous batching for mamba kernels (#1055)
|
2 mesi fa |
AlpinDale
651678d2df
VLM: use `SequenceData.from_token_counts` to create dummy data (#1093)