| .. |
|
__init__.py
|
07aa2a492f
upstream: add option to specify tokenizer
|
1 year ago |
|
block.py
|
7df7b8ca53
optimization: reduce end-to-end overhead from python obj allocation (#666)
|
5 months ago |
|
config.py
|
349a612338
chore: bump bitsandbytes version to latest; enable cuda graphs for 4bit bnb (#1123)
|
5 days ago |
|
connections.py
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
5 months ago |
|
envs.py
|
172dee2573
(2/N) Triton Backend: integrate Triton activation kernels (#1126)
|
3 days ago |
|
grammar.py
|
8a71788372
Add OLMoE (#772)
|
4 months ago |
|
logger.py
|
22a4cd4595
core: fix spec decode metrics and envs circular import (#889)
|
1 month ago |
|
logits_processor.py
|
8a71788372
Add OLMoE (#772)
|
4 months ago |
|
outputs.py
|
5b03d67abb
Core: add output streaming support to multi-step + async (#1112)
|
2 weeks ago |
|
pooling_params.py
|
2f61644f6e
SPMD optimizations (#824)
|
2 months ago |
|
sampling_params.py
|
f20f5c3491
samplers: improved DRY performance (#1108)
|
2 weeks ago |
|
sequence.py
|
5b03d67abb
Core: add output streaming support to multi-step + async (#1112)
|
2 weeks ago |
|
test_utils.py
|
8a71788372
Add OLMoE (#772)
|
4 months ago |
|
utils.py
|
172dee2573
(2/N) Triton Backend: integrate Triton activation kernels (#1126)
|
3 days ago |
AlpinDale
172dee2573
(2/N) Triton Backend: integrate Triton activation kernels (#1126)