Features Speculative Decoding
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
|
About the Speculative Decoding category
|
|
0 | 92 | March 20, 2025 |
|
Allow agent to change speculative_tokens in each request
|
|
1 | 81 | September 24, 2026 |
|
DeepSeek MTP full cuda graph support?
|
|
3 | 269 | April 13, 2026 |
|
Qwen3.5-27B-FP8 Speculative Decoding
|
|
2 | 2641 | April 11, 2026 |
|
Distributed Speculative Decoding using Ray
|
|
3 | 324 | February 11, 2026 |
|
Standalone draft model spec decode support in v0.x and v1
|
|
3 | 419 | January 20, 2026 |
|
Does vllm support draft model use tp>1 when I use speculative decoding
|
|
1 | 344 | July 29, 2025 |
|
Improving Speculative Decoding for Beginning Tokens & Structured Output
|
|
1 | 238 | July 16, 2025 |
|
Question: Specifying Medusa Choice Tree in vllm
|
|
1 | 137 | July 11, 2025 |
|
How to use speculative decoding?
|
|
3 | 1278 | May 1, 2025 |
|
Spec decode with eagle get very low Draft acceptance rate
|
|
1 | 537 | April 25, 2025 |
|
Goodput Guided Speculative Decoding
|
|
2 | 333 | April 19, 2025 |
|
Why remove bonus token of requset in draft model?
|
|
0 | 74 | March 30, 2025 |