vh/esh-pfi-infrastructure
1
0
Fork 0
Code Issues 7 Pull Requests Actions Packages Projects Releases Wiki Activity

docs(flash-next-seat): correct gateway alias list against live /model/info (summarizer/classifier are gen-small's)

Browse Source
This commit is contained in:
vh
2026-09-26 00:07:50 -07:00
parent e4cab7f430
commit 45484a0007
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
stacks/flash-next-seat/README.md
+1 -1
View File
@@ -15,7 +15,7 @@ stream with async prefetch.
| In host RAM | 47.7 GiB pinned, FP8 E4M3, 8 `model-plefp8-*` shards + one global BF16 scale |
| Context | **262,144** (full native) — KV 344,155 tokens, 1.31x concurrency |
| Speculative decoding | **MTP k=3** — 60.4% acceptance, mean acceptance length 2.81 (measured here, n=5) |
| Gateway wiring | **8 aliases** — gen, gen-reasoning, summarizer(-large), classifier, chat-judge, image-judge, qwen-image-bench |
| Gateway wiring | **8 aliases** (live `/model/info`, 2026-09-26) — gen, gen-reasoning, gen-large, summarizer-large, classifier-large, chat-judge, image-judge, qwen-image-bench. Plain `summarizer` and `classifier` go to gen-small |
> **Upstream check, 2026-09-26:** orcarouter's only commit since our 2026-09-14
> download (`c1209bda`) is `38efbff` (2026-09-18). It **adds `repack_sm70.py`**, a