fix:rename VLLM_SPYRE ENV to SENDNN_INFERENCE (#60)

Signed-off-by: Omobayode Fagbohungbe <omobayode.fagbohungbe@email.com>
Co-authored-by: Omobayode Fagbohungbe <omobayode.fagbohungbe@email.com>

Align LLM.generate with Modern vLLM API for Static mode (#57)

added full support on client metrics

Add --seq to run multi clients in sequence

Remove prometheus prints (#54)

Signed-off-by: Thara Palanivel <130496890+tharapalanivel@users.noreply.github.com>

Add multi-client support and telemetry fields (#53)

Signed-off-by: Zhuoran-Liu <zhuoran.liu@ibm.com>

Add support for multi-client runs

Signed-off-by: Nelson Mimura Gonzalez <nelson@ibm.com>

Merge pull request #49 from IBM/process

Adapt `process` to new updates

Merge pull request #48 from IBM/runner

append server.log to runner.log in server mode

Update README.md