 AlpinDale
|
4ddc14d653
core: use flashinfer for FP8 KV when available (#944)
|
преди 1 месец |
|
AlpinDale
|
22a4cd4595
core: fix spec decode metrics and envs circular import (#889)
|
преди 1 месец |
|
AlpinDale
|
901900854e
chore: consolidate environment variables within one file (#882)
|
преди 1 месец |
|
AlpinDale
|
5d37ec1016
suppress tpu import warning (#696)
|
преди 4 месеца |
|
AlpinDale
|
bf88c8567e
feat: mamba model support (#674)
|
преди 4 месеца |
|
AlpinDale
|
308501daa5
fix: default api port and attention selector (#634)
|
преди 5 месеца |
|
AlpinDale
|
a0e446a17d
feat: initial encoder-decoder support with BART model (#633)
|
преди 5 месеца |
|
AlpinDale
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
преди 5 месеца |
|
AlpinDale
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
преди 8 месеца |
