dank/serverAppConfigs
1
0 Fork 0
Code Issues 4 Pull Requests Actions Packages Projects Releases Wiki Activity

docs: FastFlowLM NPU research — AMD NPU runtime, 50 TOPS Strix Halo fit analysis, verified install state, test runbook (2026-08-16)

Browse Source
This commit is contained in:
Frank committed 2026-08-16 12:29:11 -07:00
1 parent 934c6d8be1
commit 0799fc5eb4
3 files changed
+230
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/index.md
+1
View File
@@ -57,6 +57,7 @@ Vulkan0 backend, port 7770, PARALLEL=2]
- [[frank-default-small-benchmark]] — ncmoe and batch/ubatch sweep that drove the Dankserver state
- [[dankserver-vram-growth]] — VRAM/RAM growth investigation behind the recurring cuBLAS crash on frank-default-small
- [[Dankclaw Improvements]] — researched enhancements: self-hosted agentic tools, runtime tuning, server/OS settings
- [[FastFlowLM NPU Inference]] — FastFlowLM (FLM), the AMD NPU-first runtime. The 50 TOPS Strix Halo NPU on Dankclaw: model fit, vendor benchmarks, verified install state, test runbook (2026-08-16)
## Speculative Decoding & Quantization