Frank
a34322aeb0
The managed-skill library was regenerated: 94 narrow per-incident skills
replaced by 25 broader ones (radiance-*, llamacpp-*, homepage-*, fleet/
endpoint ops). Git renders this as mass delete + mass add because whole
directories changed name; old content stays in history at 12c5e88.
Surface check: the 25 on disk are exactly the skills the harness advertises
this session.
1.7 KiB
name, description
| name | description |
|---|---|
| llama-server-arch-verify | Verify llama.cpp binary supports a model architecture without relying on binary grep |
llama-server Arch Verification
Problem
grep -ac <arch> llama-server returns 0 for ALL architecture names (including ones the binary is actively serving). The arch strings are stored in a packed/constructed form that grep can't catch.
Solution
Verify arch support via the source registration table, not binary grep:
-
Check the source registration (
src/llama-arch.cpporsrc/llmarch.h):grep -n "gemma4\|qwen3_5\|<arch>" src/llama-arch.cppIf the arch is registered in the source at the commit the binary was built from, it's supported.
-
Verify the binary is current:
stat -c "%y" /path/to/llama-server git log -1 --format=%cd <commit>The binary mtime should be after the commit date.
-
Check for model-specific source files:
ls src/models/<arch>.cpp src/models/<arch>-*.cpp 2>/dev/null -
Check for spec-type support (for MTP/draft models):
/path/to/llama-server --help 2>&1 | grep "spec-type\|model-draft"
KV Cache Types
The build's allowed --cache-type-k / --cache-type-v values:
f32, f16, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1
No true fp8 KV dtype — q8_0 is the "FP8 class" (1.0625 B/elem, 8.5 effective bits).
Separate Draft Model (MTP assistant)
For models where the MTP head is a SEPARATE file (not in-file like Swift):
--spec-type draft-mtp \
--spec-draft-n-max 3 \
--spec-draft-model /path/to/mtp-assistant.gguf
The --spec-draft-model flag (aka -md, --model-draft) loads the separate draft file.