[Speculative Decoding] Support Multi Step MTP#1
Conversation
Signed-off-by: Lu Fang <fanglu@fb.com>
Signed-off-by: Lu Fang <fanglu@fb.com>
|
👋 Hi! Thank you for contributing to the vLLM project. 💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels. Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging. To run CI, PR reviewers can either: Add 🚀 |
13996aa to
74a6aa7
Compare
74a6aa7 to
738dfca
Compare
738dfca to
a87488e
Compare
cc0410d to
f0d3627
Compare
c3873ff to
d705f84
Compare
To support real multi step implementation of MTP with K > 1