issue/832: random sample支持repetition_penalty #845
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Outdated suggestions cannot be applied.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.
API 更新 (
include/infiniop/ops/random_sample.h)infiniopRandomSample()中添加了previous_tokens和previous_tokens_len参数previous_tokens应仅包含唯一 token ID(vLLM 风格)previous_tokens为 NULL/空时回退到全历史惩罚(向后兼容)CPU/Metax 实现
previous_tokens数组中的 token 应用惩罚(如果提供)topk(0 或 -1 表示考虑所有 token,类似 vLLM)测试框架 (
test/infiniop/random_sample.py)previous_tokens(唯一 token)的测试用例previous_tokens(全历史回退)c_uint32处理previous_tokens