feat: add vLLM SDK backend for evaluation and self-evolution scripts#46
Open
Yan0613 wants to merge 1 commit into
Open
feat: add vLLM SDK backend for evaluation and self-evolution scripts#46Yan0613 wants to merge 1 commit into
Yan0613 wants to merge 1 commit into
Conversation
Add a `vllm` SDK backend across all run/eval scripts so the project can target a self-hosted vLLM OpenAI-compatible server for local inference with open-weight models (Qwen, Gemma, etc.). Changes - scripts/run_loop.py, run_eval_dabstep.py, run_eval_sealqa.py, run_eval_livecodebench.py: add `--sdk vllm` choice with `--vllm-base-url`, `--vllm-max-tokens`, `--vllm-context-length` flags wired through `set_vllm_config`. - serve_vllm.sh: helper script to launch a vLLM OpenAI server. Notes - run_eval.py keeps the upstream SDK set unchanged (no vLLM wiring there yet). - HuggingFace direct SDK is intentionally not included; vLLM covers the same open-weight use case with much better throughput.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Add a
vllmSDK backend across all run/eval scripts so the project can target a self-hosted vLLM OpenAI-compatible server for local inference with open-weight models (Qwen, Gemma, etc.).Changes
--sdk vllmchoice with--vllm-base-url,--vllm-max-tokens,--vllm-context-lengthflags wired throughset_vllm_config.