feat: GPU context 256K→128K fleet-wide + Genesis Hermes V3 on Strix Halo #20

Merged
jerome merged 5 commits from feat/gpu-128k-genesis-hermes-v3-20260717 into master 2026-07-17 11:21:32 +00:00
Showing only changes of commit 4a1f476623 - Show all commits
+4
View File
@@ -1,6 +1,10 @@
--- ---
name: inference-optimization name: inference-optimization
kind: responsibility kind: responsibility
description: >
Optimizes the full Syslog inference stack — LiteLLM routing weights, GPU model
assignments, agent context management, and prompt caching — to reduce response
times to sub-15s average. All GPUs now at 128K context (stable ceiling).
id: 067NC6KP02RG60S50M40E30928 id: 067NC6KP02RG60S50M40E30928
--- ---