 AlpinDale
|
9f3d6205ce
fix ray gpu executor
|
7 months ago |
 AlpinDale
|
236be273e5
feat: tensor parallel speculative decoding (#554)
|
7 months ago |
|
AlpinDale
|
c6a501f682
add multiprocessing executor; make ray optional
|
7 months ago |
|
AlpinDale
|
ef733aee43
implement ExecuteModelData to reduce executor complexity
|
7 months ago |
|
AlpinDale
|
7bcf4c3fc9
centralize gpu worker construction
|
7 months ago |
|
AlpinDale
|
fb982981ce
num_lookahead_slots in neuron and ray executors
|
7 months ago |
|
AlpinDale
|
957ed7d244
type hints
|
7 months ago |
|
AlpinDale
|
c21af7acad
feat: `DistributedGPUExecutor` abstract class (#541)
|
8 months ago |
|
AlpinDale
|
199e776722
chore: move ray utils to executor dir
|
8 months ago |
|
AlpinDale
|
46159b107a
formatting: pt1
|
8 months ago |
|
AlpinDale
|
fca911ee0a
vLLM Upstream Sync (#526)
|
8 months ago |
|
AlpinDale
|
f894f7b176
Revert "reduce dedupe by wrapping in general worker class"
|
9 months ago |
|
AlpinDale
|
082b0b03bc
Revert "actually run the workers"
|
9 months ago |
|
AlpinDale
|
36cf32649d
actually run the workers
|
9 months ago |
|
AlpinDale
|
9fff6fb507
reduce dedupe by wrapping in general worker class
|
9 months ago |
|
AlpinDale
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
10 months ago |
|
AlpinDale
|
0f6d56b07f
feat: model executor refactor (#367)
|
11 months ago |
|
AlpinDale
|
f8dfac6372
chore: attention refactor and upstream sync apr01 (#365)
|
11 months ago |
