File tree Expand file tree Collapse file tree
Expand file tree Collapse file tree Original file line number Diff line number Diff line change @@ -77,7 +77,12 @@ Open items: extending the parallel-agnostic mode to the V2 model runner and
7777to multi-group attention layouts (the two exclusions that bit here), and -
7878wherever a deployment falls in an excluded configuration - failing the pull
7979cleanly (see Defect 2) and having the router avoid emitting a cross-TP
80- source header, since the pull cannot succeed there.
80+ source header, since the pull cannot succeed there. On the first item,
81+ [ vllm #48414 ] ( https://github.com/vllm-project/vllm/pull/48414 ) (stacked on
82+ #48408 ) is in flight: it stores offloaded KV in a canonical
83+ parallelism-free layout - one copy per block, no parallelism inputs in the
84+ transfer path - and fails uncertifiable configs at startup instead of
85+ silently demoting.
8186
8287Repro: ` llama-fs-crosstp.yaml ` (the two TP pods) + ` llama-fs-test.sh ` (warm,
8388cross-read, on-disk hash-dir dump).
You can’t perform that action at this time.
0 commit comments