docs(research): add qwen3.8-27b decode speed analysis

Browse Source

- Add research note on decode tokens/s versus context depth for Qwen3.8-27B + DFlash2 on the R9700
- Covers draft length (5, not 7), acceptance falling with depth, bandwidth ceiling, and an ordered experiment plan. Proposals only, nothing applied
- Index the note in docs/research/README.md
- Also stages .serena/ project config and llmserver.log

...

This commit is contained in:

haylan committed 2026-11-11 16:51:45 +01:00

1 parent 5b866b93ff

commit e5cc2a6360

5 files changed

+10416

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

llmserver.log

+10000

File diff suppressed because it is too large. Load diff