Dflash: Block Diffusion Speculative Decoding#995
Draft
vjanfaza wants to merge 2 commits into
Draft
Conversation
Co-authored-by: Vahid Janfaza <vjanfaza@qti.qualcomm.com> Co-authored-by: fannanya <fannanya@qti.qualcomm.com> Signed-off-by: Vahid Janfaza <vjanfaza@qti.qualcomm.com>
quic-rishinr
requested review from
jinkasaisagar,
quic-amitraj,
quic-rishinr and
vbaddi
and removed request for
jinkasaisagar and
quic-amitraj
Co-authored-by: Vahid Janfaza <vjanfaza@qti.qualcomm.com> Co-authored-by: fannanya <fannanya@qti.qualcomm.com> Signed-off-by: Vahid Janfaza <vjanfaza@qrc706r8-292-10.qualcomm.com>
Contributor
|
Design discussion pending. |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
In this PR, we are adding the support for DFlash (Block Diffusion for Flash Speculative Decoding) approach that significantly accelerate LLM inference on Qualcomm platforms.
DFlash replaces autoregressive draft models with a diffusion-based block drafter that predicts an entire block of tokens in a single parallel pass, resulting in constant drafting latency independent of block size.
Key benefits:
5–6× lossless speedup over baseline decoding
~2.5× faster than EAGLE-3
Higher acceptance length enabled by KV injection of target hidden states into every draft layer
Improved accelerator utilization and reduced end-to-end latency
Verification is performed by the frozen target model, guaranteeing output identical to standard decoding.
Use-case(s)
High-throughput and low-latency LLM serving
Long chain-of-thought reasoning workloads (e.g., math and planning)
Code generation and agentic inference loops
Platform differentiation via advanced speculative decoding on AI100
#Requirements
DFlash speculative decoding with block diffusion drafting and target verification
Extraction and fusion of hidden states from multiple target layers during prefill
KV cache injection of fused target context into all draft layers
Integration with QEfficient, vLLM, and other applications
Support current architecture:
Target: single QPC for prefill + decode (expandable to DA serving)
Draft: lightweight QPC
Equally Contributors