Deniss Abramovs

Results 68 comments of Deniss Abramovs

> Streaming is now supported via SSE. gRPC streaming will requires streaming support for gRPC on BentoML. I'm going to transfer this to BentoML for now since SSE should be...

Everything is working if path added to ignore list or fileUploader set to false.

I'm trying `pip install git+https://github.com/HazyResearch/flash-attention.git#subdirectory=csrc/rotary` and getting this error: ``` Collecting git+https://github.com/HazyResearch/flash-attention.git#subdirectory=csrc/rotary Cloning https://github.com/HazyResearch/flash-attention.git to /tmp/pip-req-build-fmhz3e3e Running command git clone --filter=blob:none --quiet https://github.com/HazyResearch/flash-attention.git /tmp/pip-req-build-fmhz3e3e Resolved https://github.com/HazyResearch/flash-attention.git to commit 913922cac57efd7c5e05f08155b37e74c427cf32 Running...

I guess that this counter is representing current runtime handled requests and not the whole handled requests of the queue... I guess you need another counter, which will represent totalHandledRequestCount...

Same here, need v4 client, v3 client is outdated.