Autor | SHA1 Nachricht | Datum |
---|---|---|
AlpinDale | d8a51d05a7 fix: seeded gens with pipeline parallel | vor 5 Monaten |
AlpinDale | 2c653a2268 fix: make speculative decoding work with per-request seed | vor 5 Monaten |
AlpinDale | 7253e9052d feat: integrate typical acceptance sampling for spec decoding | vor 5 Monaten |
AlpinDale | 313e6e1ec7 feat: add typical acceptance sampling | vor 5 Monaten |