text-generation-inference/backends
Daniël de Kok c7b495f97d hotfix: avoid non-prefilled block use when using prefix caching (#2489)
The minimum batch size logic could cause prefix blocks to be
deallocated without prefill. The next allocation of the same
prefix would then use garbage blocks.
2024-09-25 06:13:11 +00:00
..
client Lots of improvements (Still 2 allocators) (#2449) 2024-09-25 06:13:11 +00:00
grpc-metadata Rebase TRT-llm (#2331) 2024-09-25 05:55:39 +00:00
trtllm More fixes trtllm (#2342) 2024-09-25 06:08:00 +00:00
v3 hotfix: avoid non-prefilled block use when using prefix caching (#2489) 2024-09-25 06:13:11 +00:00