Add link to online SFT in speculative training section (#250)

Updated the speculative training section to include a link for online SFT on the draft model.

Author: zhaochenyang20

blog/2025-11-19-miles.md

@@ -55,7 +55,7 @@ In order to fully utilize the precious GPU memory for maximum performance withou
 
 ### Speculative Training
 
-In RL, freezing the draft model prevents it from following the target model policy, reducing accept length and degrading speedup, so we perform online SFT on the draft model throughout RL.
+In RL, freezing the draft model prevents it from following the target model policy, reducing accept length and degrading speedup, so we perform [online SFT on the draft model](https://github.com/zhaochenyang20/Awesome-ML-SYS-Tutorial/blob/main/rlhf/slime/spec/readme-en.md) throughout RL.
 
 - Achieve 25%+ rollout speedup vs. frozen MTP, especially in the late training stage.
 - Support MTP with sequence packing + CP; Loss masks with proper edge-case handling; LM head/embedding gradient isolation, and Megatron↔SGLang weight syncing.
@@ -82,4 +82,4 @@ For the future development of Miles, we will put together more efforts to suppor
 
 Miles exists thanks to the slime authors and the broader (SGLang) RL community.
 
-We invite researchers, startups, and enterprise teams alike to explore slime and Miles - whichever best fits your environment - and to be together with us to make reinforcement learning efficient and reliable. We'll hear from the community and actively work on Miles' future development, towards a production-ready training environment.
+We invite researchers, startups, and enterprise teams alike to explore slime and Miles - whichever best fits your environment - and to be together with us to make reinforcement learning efficient and reliable. We'll hear from the community and actively work on Miles' future development, towards a production-ready training environment.