Frank
215d74f6ce
Dankserver (frank-default-small): - Stock llama.cpp (latest master, CUDA build) replaces ik_llama.cpp - Model: peculiar-ragdoll/Tiel-Coder-35B-A3B UD-Q6_K_XL (30 GB) Architecture: qwen35moe, 40 layers (10 attn + 30 SSM), 256 experts/8 used - CTX_SIZE=200700 (66900/slot × 3 parallel), Q8_0 KV (~2 GB cache buffer) - --cpu-moe for expert offload, -ngl 999 (non-expert on GPU) - mmap enabled; removed ik_llama-specific flags Dankclaw (frank-default-large): - ROCmFPX fork with PR #27742 (qwen4exp arch) merged and built at /home/dank/GitPackages/ROCmFPX/build-qwen38 - Model: kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX_LEAN (98.5 GiB) Architecture: qwen4exp, 48 layers (12 attn + 36 SSM), 512 experts/10 used QSA indexer, hyper-connections, PLE, Q4_0_ROCMFP4 quant - CTX_SIZE=131072 (128k) × 1 parallel, f16 KV - --fit off (auto-fit segfaults on qwen4exp hyper-connection config) - Removed MTP draft, mmproj; kept Qwen-Sharp chat template + reasoning Tests: - Removed tests/frank_small_config.bats and tests/frank_large_config.bats (moved to .AGENTTRASH/). These were config-assertion tests that checked 'is variable X set to Y' rather than testing the serve script's actual behavior. All 199 remaining tests pass. - Updated test-changed.sh mappings and changed_tests.bats to reflect the removal.
89 lines
3.6 KiB
Bash
89 lines
3.6 KiB
Bash
#!/usr/bin/env bats
|
|
# Seam: frank-default-small model, context, tensor placement, and template.
|
|
# This test covers only the Q6_K deployment contract.
|
|
|
|
load helpers
|
|
|
|
ENV_FILE="$REPO_ROOT/scripts/frank-default-small.env"
|
|
SERVE_FILE="$REPO_ROOT/scripts/serve-frank-small.sh"
|
|
UNIT_FILE="$REPO_ROOT/scripts/frank-default-small.service"
|
|
TEMPLATE_FILE="$REPO_ROOT/scripts/chat-template.jinja"
|
|
|
|
@test "frank-default-small selects the Ornith Q8_0 model" {
|
|
grep -q '^MODEL_FILE=Ornith-1\.5-35B-A3B-CRACK-Q8_0\.gguf$' "$ENV_FILE"
|
|
grep -q 'Ornith-1\.5-35B-A3B-CRACK-Q8_0\.gguf' "$SERVE_FILE"
|
|
}
|
|
|
|
@test "frank-default-small uses three 163840-slot context (491520 pool)" {
|
|
grep -q '^CTX_SIZE=491520$' "$ENV_FILE"
|
|
grep -q '^PARALLEL=3$' "$ENV_FILE"
|
|
grep -q '163840 per slot' "$ENV_FILE"
|
|
}
|
|
|
|
@test "frank-default-small uses default f16 K and q6_0 V KV cache" {
|
|
grep -q '^CACHE_TYPE_K=f16$' "$ENV_FILE"
|
|
grep -q '^CACHE_TYPE_V=q6_0$' "$ENV_FILE"
|
|
# K at default f16 has no Hadamard; V at q6_0 keeps Hadamard.
|
|
grep -q '^K_CACHE_HADAMARD=0$' "$ENV_FILE"
|
|
grep -q '^V_CACHE_HADAMARD=1$' "$ENV_FILE"
|
|
}
|
|
|
|
@test "frank-default-small keeps full-attention and final blocks on CUDA" {
|
|
source "$ENV_FILE"
|
|
[[ "$OVERRIDE_EXPERT" == 'blk\.(0|1|2|4|5|6|8|9|10|12|13|14|16|17|18|20|21|22|24|25|26|27|28|29|30|31|32|33|34)\.ffn_(up|down|gate|gate_up)_(ch|)exps' ]]
|
|
# output-adjacent final blocks stay on CUDA
|
|
[[ "$OVERRIDE_EXPERT" != *'|35|'* ]]
|
|
[[ "$OVERRIDE_EXPERT" != *'|36|'* ]]
|
|
[[ "$OVERRIDE_EXPERT" != *'|37|'* ]]
|
|
[[ "$OVERRIDE_EXPERT" != *'|38|'* ]]
|
|
[[ "$OVERRIDE_EXPERT" != *'|39|'* ]]
|
|
[[ "$OVERRIDE_EXPERT" != *'|40|'* ]]
|
|
# full-attention blocks (3,7,11,15,19,23) are untouched (no exps)
|
|
[[ "$OVERRIDE_EXPERT" != *'|3|'* ]]
|
|
[[ "$OVERRIDE_EXPERT" != *'|7|'* ]]
|
|
[[ "$OVERRIDE_EXPERT" != *'|11|'* ]]
|
|
[[ "$OVERRIDE_EXPERT" != *'|15|'* ]]
|
|
[[ "$OVERRIDE_EXPERT" != *'|19|'* ]]
|
|
[[ "$OVERRIDE_EXPERT" != *'|23|'* ]]
|
|
[[ "$OVERRIDE_BUFT" == CPU ]]
|
|
# ik_llama --gpu-layers/-ngl requires an integer ("all" is rejected); 999
|
|
# loads as many layers as possible while OVERRIDE_EXPERT pins exps to CPU.
|
|
[[ "$N_GPU_LAYERS" == 999 ]]
|
|
}
|
|
|
|
@test "frank-default-small disables speculative decoding (3 parallel slots)" {
|
|
# ik_llama limits speculative decoding to -np 1; with PARALLEL=3 a
|
|
# configured spec stage hard-exits, so SPEC_TYPE=none.
|
|
grep -q '^SPEC_TYPE=none$' "$ENV_FILE"
|
|
grep -q '^PARALLEL=3$' "$ENV_FILE"
|
|
! grep -q '^SPEC_NGRAM_MOD_N_MIN=' "$ENV_FILE"
|
|
! grep -q '^SPEC_NGRAM_MOD_N_MAX=' "$ENV_FILE"
|
|
! grep -q '^SPEC_NGRAM_MOD_N_MATCH=' "$ENV_FILE"
|
|
! grep -q -- 'SPEC_DRAFT_' "$ENV_FILE"
|
|
! grep -q -- '--spec-type.*draft-mtp' "$SERVE_FILE"
|
|
grep -q -- '--spec-type' "$SERVE_FILE"
|
|
! grep -q -- 'ngram' "$SERVE_FILE"
|
|
}
|
|
|
|
@test "frank-default-small uses ubatch 1024" {
|
|
grep -q '^BATCH_SIZE=4096$' "$ENV_FILE"
|
|
grep -q '^UBATCH_SIZE=1024$' "$ENV_FILE"
|
|
grep -q ': "${UBATCH_SIZE:=1024}"' "$SERVE_FILE"
|
|
}
|
|
|
|
@test "frank-default-small uses the tracked Qwen-Sharp template" {
|
|
grep -q '^CHAT_TEMPLATE_FILE=' "$ENV_FILE"
|
|
grep -q 'peculiar-ragdoll/Qwen-Sharp-Chat-Templates' "$ENV_FILE"
|
|
grep -q 'chat-template\.jinja' "$SERVE_FILE"
|
|
[ -s "$TEMPLATE_FILE" ]
|
|
grep -q 'qwen3\.8-froggeric-v22\.4\.0' "$TEMPLATE_FILE"
|
|
grep -q 'Qwen-Sharp' "$UNIT_FILE"
|
|
}
|
|
|
|
@test "frank-default-small renders the custom template with --jinja" {
|
|
# Without --jinja, ik_llama only supports built-in non-Jinja handlers and
|
|
# silently drops the custom Qwen-Sharp template formatting.
|
|
grep -q '^USE_JINJA=1$' "$ENV_FILE"
|
|
grep -q -- '--jinja' "$SERVE_FILE"
|
|
}
|