text-generation-inference/router/src
Karol Damaszke bf5263b88b
Disable watermark with FP8 quantization (#114)
Co-authored-by: Karol Damaszke <kdamaszke@habana.ai>
2024-03-27 13:32:20 +01:00
..
health.rs Rebased #617 (#868) 2023-08-28 11:43:47 +02:00
infer.rs Revert "Prefer prefill instead of decode when max_waiting_tokens==0 (#18)" (#45) (#76) 2024-02-27 11:56:45 +01:00
lib.rs Exllama v2 (#1211) 2023-11-25 22:38:38 +01:00
main.rs Adjust warmup to all possible bucket sizes and decode batch size = 1 (#113) 2024-03-27 11:59:51 +01:00
queue.rs Heap based router queue (#63) (#88) 2024-02-29 10:56:26 +01:00
server.rs Control prefill and decode batch size separately (#6) 2024-01-02 18:21:01 +01:00
validation.rs Disable watermark with FP8 quantization (#114) 2024-03-27 13:32:20 +01:00