Add tokenizer longhaul cache

This commit is contained in:
Owen Qwen
2026-07-30 23:32:52 -05:00
parent a673afad85
commit e0665b1042
21 changed files with 1078 additions and 23 deletions
+2
View File
@@ -57,6 +57,8 @@ test parameters:
-ctk, --cache-type-k <t> (default: f16)
-ctv, --cache-type-v <t> (default: f16)
--longhaul-cache <GiB> expert cache size for longhaul mode
--tokenizer-longhaul page tokenizer indexes through a bounded cache
--tokenizer-longhaul-cache <MiB> tokenizer lookup cache size
-t, --threads <n> (default: system dependent)
-C, --cpu-mask <hex,hex> (default: 0x0)
--cpu-strict <0|1> (default: 0)