frank-primary: pin radiance v1.2.0, translate expert-vs-cache-ratio to vram knobs
Engine v1.2.0 (Codeberg e95d397, Docker Hub tag 1.2.0, index digest 665775ed...) removes --expert-vs-cache-ratio. The explicit --vram-weights-mib 26071 / --vram-kv-mib 3543 pair transcribes the live 1.0.13 boot ledger at ratio 0.82 (weights 25.46 GiB, KV 3.46 GiB per card); bracket arms scale KV linearly in (1-r): 0.90 -> 1968, 0.95 -> 984. Serve script, autoresearch harness, and bats gates follow; the bats shape asserts are realigned to the deployed seqs=3/spec=2 sweep result (95923d3,df6b5bb) they failed to track.
This commit is contained in:
1 parent
9aee00f2b3
commit
0258ae0897
4 files changed
+34
-14
No files matched your search
@@ -50,7 +50,8 @@ set +a
|
||||
: "${FRANK_PRIMARY_PLACEMENT:?FRANK_PRIMARY_PLACEMENT must be set}"
|
||||
: "${FRANK_PRIMARY_HOST_POOL_MIB:?FRANK_PRIMARY_HOST_POOL_MIB must be set}"
|
||||
: "${FRANK_PRIMARY_GPU_HEADROOM_MIB:?FRANK_PRIMARY_GPU_HEADROOM_MIB must be set}"
|
||||
: "${FRANK_PRIMARY_EXPERT_VS_CACHE:?FRANK_PRIMARY_EXPERT_VS_CACHE must be set}"
|
||||
: "${FRANK_PRIMARY_VRAM_WEIGHTS_MIB:?FRANK_PRIMARY_VRAM_WEIGHTS_MIB must be set}"
|
||||
: "${FRANK_PRIMARY_VRAM_KV_MIB:?FRANK_PRIMARY_VRAM_KV_MIB must be set}"
|
||||
: "${FRANK_PRIMARY_KV_DTYPE:?FRANK_PRIMARY_KV_DTYPE must be set}"
|
||||
: "${FRANK_PRIMARY_SPEC_TOKENS:?FRANK_PRIMARY_SPEC_TOKENS must be set}"
|
||||
: "${FRANK_PRIMARY_MAX_BATCHED_TOKENS:?FRANK_PRIMARY_MAX_BATCHED_TOKENS must be set}"
|
||||
@@ -186,7 +187,8 @@ podman run -d --name "$FRANK_PRIMARY_CONTAINER" \
|
||||
--placement "$FRANK_PRIMARY_PLACEMENT" \
|
||||
--host-pool-mib "$FRANK_PRIMARY_HOST_POOL_MIB" \
|
||||
--gpu-headroom-mib "$FRANK_PRIMARY_GPU_HEADROOM_MIB" \
|
||||
--expert-vs-cache-ratio "$FRANK_PRIMARY_EXPERT_VS_CACHE" \
|
||||
--vram-weights-mib "$FRANK_PRIMARY_VRAM_WEIGHTS_MIB" \
|
||||
--vram-kv-mib "$FRANK_PRIMARY_VRAM_KV_MIB" \
|
||||
--kv-cache-dtype "$FRANK_PRIMARY_KV_DTYPE" \
|
||||
--prefix-cache-host-mib "$FRANK_PRIMARY_PREFIX_HOST_MIB" \
|
||||
--prefix-cache-dir /data/kvcache/frank-primary \
|
||||
|
||||
Reference in new issue
Block a user