| .. |
|
models
|
9c1bea97e8
fix embed_tokens for last layer in qwen models
|
hai 3 meses |
|
__init__.py
|
5bbde22a23
move everything under exo module
|
hai 9 meses |
|
losses.py
|
38e368f00b
Fixed up the ops so that batches work
|
hai 4 meses |
|
perf_improvements.md
|
c9ded9ba96
optimise networking, remove bloat
|
hai 4 meses |
|
sharded_inference_engine.py
|
af171f06fa
propagate prompts to other nodes so they can display them, cleaner prompt/output output
|
hai 3 meses |
|
sharded_utils.py
|
9986fb86d4
remove prints and fix download progress for SD
|
hai 4 meses |
|
test_non_blocking.py
|
3c7bd48aa3
get rid of some more hf bloat
|
hai 3 meses |
|
test_sharded_model.py
|
f53056dede
more compact operator formatting
|
hai 8 meses |
Alex Cheema
9c1bea97e8
fix embed_tokens for last layer in qwen models