Skip to content

Add --nar-chunk to cap the acoustic chunk below what the context holds - #26

Open
timoncool wants to merge 1 commit into
ServeurpersoCom:masterfrom
timoncool:nar-chunk
Open

timoncool wants to merge 1 commit into
ServeurpersoCom:masterfrom
timoncool:nar-chunk

Conversation

@timoncool

Copy link
Copy Markdown

The acoustic stage cuts a song into chunks of (context - prefix - 3) / 2 frames, so the only way to make a chunk
smaller today is --max-seq, which also shrinks the room the semantic stage has for the song. Without flash
attention that is the lever people reach for, because a chunk's attention scores grow with the square of its length,
and it costs them the end of long songs.

--nar-chunk <frames> (yue-server and yue-synth) caps the chunk length on its own; 0, the default, keeps the
current rule. The semantic stage keeps the whole context.

Measured on an RTX 4090, Q8_0, --no-fa, the same request and seeds (a 240 s song, prompt 2549 tokens):

chunk (frames) peak VRAM over idle acoustic stage
6000 (one chunk, full context) 12.0 GB 97 s
3332 + 2718 (--max-seq 9216) 5.7 GB 65 s
3000 + 3000 + 100 (--nar-chunk 3000, full context) 5.9 GB 65 s

With flash attention on the same song takes 4.2 GB in one chunk and 3.5 GB in two. The level around the joins
matches the one-chunk render within 1–2 dB, with no gap.

README and ARCHITECTURE list the flag and say when it helps.

cynodesmus added a commit to cynodesmus/yue2.cpp that referenced this pull request Nov 19, 2026
[PR ServeurpersoCom#26] Add --nar-chunk to cap the acoustic chunk below what the context holds
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant