| .. |
|
__init__.py
|
04b53d2db5
chore: add initializer files
|
hace 1 año |
|
cache_engine.py
|
f40b809d3b
allow using v2 block manager with sliding window
|
hace 7 meses |
|
cpu_model_runner.py
|
8d77c69cbd
feat: support image processor and add llava example
|
hace 7 meses |
|
cpu_worker.py
|
50b7c13db0
refactor: attention selector (#552)
|
hace 8 meses |
|
embedding_model_runner.py
|
8d77c69cbd
feat: support image processor and add llava example
|
hace 7 meses |
|
model_runner.py
|
6cecbbff6a
fix: reduce memory footprint of cuda graph by adding output buffer
|
hace 7 meses |
|
neuron_model_runner.py
|
35ae01d7ba
refactor: attention metadata term
|
hace 8 meses |
|
neuron_worker.py
|
fca911ee0a
vLLM Upstream Sync (#526)
|
hace 8 meses |
|
worker.py
|
eb2c5c77df
feat: enforce the max possible seqlen
|
hace 7 meses |
|
worker_base.py
|
7194047318
remove vllm-nccl
|
hace 7 meses |
AlpinDale
6cecbbff6a
fix: reduce memory footprint of cuda graph by adding output buffer