 AlpinDale
|
fa84f8102e
kernels: split marlin kernels for faster compile, fix MoE, temporarily remove HQQ (#1119)
|
vor 6 Tagen |
|
AlpinDale
|
fd07406a19
fix: grouped_topk return type (#1038)
|
vor 1 Monat |
 AlpinDale
|
201db10f02
models: add support for Phi3 MoE
|
vor 1 Monat |
|
AlpinDale
|
9f3e7c86e2
feat: add fused Marlin MoE kernel (#934)
|
vor 1 Monat |
|
AlpinDale
|
22a4cd4595
core: fix spec decode metrics and envs circular import (#889)
|
vor 1 Monat |
|
AlpinDale
|
901900854e
chore: consolidate environment variables within one file (#882)
|
vor 2 Monaten |
|
AlpinDale
|
81c28d2a7f
fix: use nvml to get consistent device names (#739)
|
vor 4 Monaten |
|
AlpinDale
|
d34e083c48
feat: add experts_int8 support (#730)
|
vor 5 Monaten |
|
AlpinDale
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
vor 5 Monaten |
|
AlpinDale
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
vor 9 Monaten |
|
AlpinDale
|
f8dfac6372
chore: attention refactor and upstream sync apr01 (#365)
|
vor 10 Monaten |
