Ronen Schaffer
Ronen Schaffer
This PR adds the Prometheus metrics defined in #2650
**BEFORE SUBMITTING, PLEASE READ THE CHECKLIST BELOW AND FILL IN THE DESCRIPTION ABOVE** --- PR Checklist (Click to Expand) Thank you for your contribution to vLLM! Before submitting the pull...
When sampling is enabled, we might miss important events such as establishment and termination of TCP connections. It may be useful to add a setting that makes the agent always...
# Issue link # What changes have been made - Added `go vet` to the Makefile - Fixed its errors # Verification steps ## Checks - [ ] I've made...
# Issue link # What changes have been made This is another take on #573 to add initial metrics considering the redesign of codeflare-operator. # Verification steps I checked that...
# Issue link Closes #674 # What changes have been made This PR adds a custom metric to expose how many AppWrappers are per state. It is built on top...
# Issue link # What changes have been made This PR adds custom histogram metrics of a of the requested resources (CPU, Memory and GPU) by the AppWrappers. # Verification...
### Name of Feature or Improvement A metric of AppWrappers count per state ### Description of Problem the Feature Should Solve How many AppWrappers are in each state (Pending, Runing,...
After merging #7049, I noticed that non-beam search requests result in duplicate OpenTelemetry spans being exported. This PR resolves the issue by passing the `finished_before` list to `do_tracing()`, similar to...
### Which component is this bug for? Langchain Instrumentation ### 📜 Description I am using the OpenLLMetry `LangchainInstrumentor` to instrument `VLLMOpenAI` in LangChain. Both vLLM and the `LangchainInstrumentor` are configured...