dank/serverAppConfigs
1
0 Fork 0
Code Issues 4 Pull Requests Actions Packages Projects Releases Wiki Activity

docs(radiance): correct the tokeniser corpus name and statsdump auth note

Browse Source
This commit is contained in:
Frank committed 2026-10-30 15:03:31 -07:00
1 parent 6e80cd44f0
commit bdc0613739
2 files changed
+3 -2
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

serverAppConfigs-docs/LLM/Radiance Operations.md
+2 -1
View File
@@ -181,7 +181,8 @@ refusal**, not an engine fault: read the journal line and the argv, not the GPU.
proposals held, KV bytes and the tokens they address, stream misses and bytes, prefix hits and proposals held, KV bytes and the tokens they address, stream misses and bytes, prefix hits and
evictions, preemptions and queue depth. `/stats`, evictions, preemptions and queue depth. `/stats`,
`/graph`, `/sessions` back the dashboard. `scripts/statsdump.py` records `/stats` to JSONL with `/graph`, `/sessions` back the dashboard. `scripts/statsdump.py` records `/stats` to JSONL with
time and gap, for a machine with no scraper. time and gap, for a machine with no scraper (its key comes from `--api-key` or
`RADIANCE_API_KEY`).
- `RADIANCE_PROFILE_EVERY`, `RADIANCE_DUMP_BUF`/`RADIANCE_DUMP_DIR`, `RADIANCE_OP_ORACLE`(+) and the - `RADIANCE_PROFILE_EVERY`, `RADIANCE_DUMP_BUF`/`RADIANCE_DUMP_DIR`, `RADIANCE_OP_ORACLE`(+) and the
`RADIANCE_DEBUG_*` family are debug instruments; they are not deployment settings. `RADIANCE_DEBUG_*` family are debug instruments; they are not deployment settings.
serverAppConfigs-docs/LLM/Radiance Tools.md
+1 -1
View File
@@ -255,7 +255,7 @@ eight-rank all-reduce shard weights and times `lockstep`/`ring`/`split` forms at
``` ```
rad-tokcheck [options] <tokenizer.json> <corpus-file>... rad-tokcheck [options] <tokenizer.json> <corpus-file>...
--hf-dir DIR compare against HuggingFace ids in DIR/<corpus>.ids --hf-dir DIR compare against HuggingFace ids in DIR/<corpus basename>.ids
(little-endian int32, encode(text, add_special_tokens=False)) (little-endian int32, encode(text, add_special_tokens=False))
--no-ref skip the reference encoder (slow) --no-ref skip the reference encoder (slow)
--user encode with parse_special off --user encode with parse_special off