| .. |
|
__init__.py
|
07aa2a492f
upstream: add option to specify tokenizer
|
1 år sedan |
|
block.py
|
7df7b8ca53
optimization: reduce end-to-end overhead from python obj allocation (#666)
|
4 månader sedan |
|
config.py
|
7ca63930c8
support deepseek_v3 model
|
1 vecka sedan |
|
connections.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
4 månader sedan |
|
envs.py
|
ddaefd8d38
chore: remove engine_use_ray (#1024)
|
1 vecka sedan |
|
grammar.py
|
8a71788372
Add OLMoE (#772)
|
2 månader sedan |
|
logger.py
|
22a4cd4595
core: fix spec decode metrics and envs circular import (#889)
|
3 veckor sedan |
|
logits_processor.py
|
8a71788372
Add OLMoE (#772)
|
2 månader sedan |
|
outputs.py
|
0e558e9b2f
fix: loading chameleon model with TP>1 (#695)
|
4 månader sedan |
|
pooling_params.py
|
2f61644f6e
SPMD optimizations (#824)
|
1 månad sedan |
|
sampling_params.py
|
8d9f1fd4e6
feat: add single user mode (#927)
|
2 veckor sedan |
|
sequence.py
|
411ac4f405
vlm: add support for Qwen2-VL model (#1015)
|
2 veckor sedan |
|
test_utils.py
|
8a71788372
Add OLMoE (#772)
|
2 månader sedan |
|
utils.py
|
65a59bbb6b
cpu: raise error if using encoder-decoder models (#1027)
|
1 vecka sedan |
AlpinDale
7ca63930c8
support deepseek_v3 model