Author | SHA1 Message | Date |
---|---|---|
AlpinDale | d8a51d05a7 fix: seeded gens with pipeline parallel | 4 months ago |
AlpinDale | 16dff9babc chore: enable bonus token in spec decoding for KV cache based models | 5 months ago |
AlpinDale | 405bb74612 Control plane comms refactor (#573) | 5 months ago |
AlpinDale | af43576da0 feat: add MLPSpeculator speculative decoding support (#572) | 5 months ago |