Author | SHA1 Message | Date |
---|---|---|
AlpinDale | 083ba7b452 roll back chunked prefill changes to SDPA, isolate cpu worker | 9 months ago |
AlpinDale | 4d33ce60da feat: Triton flash attention backend for ROCm (#407) | 9 months ago |
AlpinDale | 9aaeb5d349 add speculative config and arg for later | 9 months ago |
AlpinDale | a304f76d89 feat: Intel CPU support (#403) | 9 months ago |