Commit 87abb7e
committed
agentx: keep prefix caching ON in kimik2.7 none cell
The none case previously passed --no-enable-prefix-caching, which disables the
on-GPU prefix cache entirely, not just DRAM offload. That crippled the no-offload
baseline (no reuse even within HBM) and made lmcache look artificially good. Leave
prefix caching at vLLM's default (ON) so none is an honest GPU-only-KV baseline,
apples-to-apples vs lmcache. Matches the kimik2.5 / dsv4 agentic recipes.1 parent de4cff8 commit 87abb7e
1 file changed
Lines changed: 6 additions & 1 deletion
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
130 | 130 | | |
131 | 131 | | |
132 | 132 | | |
133 | | - | |
| 133 | + | |
| 134 | + | |
| 135 | + | |
| 136 | + | |
| 137 | + | |
| 138 | + | |
134 | 139 | | |
135 | 140 | | |
136 | 141 | | |
| |||
0 commit comments