Backlog: F3's gaps closed and checked on the PoC, cache_salt against a real vLLM
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
1 parent
26630274f4
commit
99829b3124
1 file changed
+7
-1
+7
-1
@@ -976,7 +976,13 @@ one); `x-llmgw-sources`; before guardInput; never cached; metrics. Default colle
|
||||
wins, 30 s cache, `ctl kb default`, console action; never refuse); the
|
||||
portal chat's Documents picker (collection, default or none; sources listed
|
||||
under the answer; a header the page sends itself is dropped). `cache_salt` per organization on requests given passages, sent to vLLM
|
||||
replicas only (chosen replica's engine). Left: returned passages
|
||||
replicas only (chosen replica's engine). Checked on the PoC 2026-10-08:
|
||||
vLLM 0.30.0 (cuda01) with TinyLlama-1.1B AWQ run by hand beside the 35B in
|
||||
the card's last 2.3 GB — a 668-token prompt reused 656 tokens under the same
|
||||
salt and 0 under another's, with identical text (llmgw cannot place it
|
||||
there: placement takes whole GPUs). Live on the PoC: a team default answers
|
||||
a request without the header, `none` turns it off, an explicit header with
|
||||
k=2 gives two sources and no more, llmgw-kb lists owners by path. Left: returned passages
|
||||
are not audited per request (the header and the kept request record them).
|
||||
|
||||
### F4. Adapter training (L, after F1–F3)
|
||||
|
||||
Reference in new issue
Block a user