haylan e5cc2a6360 docs(research): add qwen3.8-27b decode speed analysis ...

- 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

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

..

agents

docs(agents): add writing-docs guide and new-term procedure

2026-09-24 21:52:19 +02:00

coding-cli-setup

docs(opencode): document v2 config, mark v1 deprecated

2026-10-05 21:32:58 +02:00

research

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

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

architecture.md

feat(llm): re-enable RAM prompt cache (8192 MiB) with --no-cache-idle-slots

2026-11-06 19:24:28 +01:00

gateway.md

feat(llm): switch to DFlash2 speculative decoding, drop qwen-classifier

2026-10-05 21:28:55 +02:00

network-access.md

feat(llm): switch to DFlash2 speculative decoding, drop qwen-classifier

2026-10-05 21:28:55 +02:00

operations.md

feat(scripts): add redownload-model.sh to force-refresh a GGUF

2026-11-11 16:36:54 +01:00

server-planing.md

Add build plan documentation for 4x Radeon AI PRO R9700 rackmount LLM server

2026-08-25 07:20:58 +02:00