diff --git a/recipes/glm-5-3-flash-4x6000-jj-mtp3/recipe.yaml b/recipes/glm-5-3-flash-4x6000-jj-mtp3/recipe.yaml index acf81b472..02ec2981d 100644 --- a/recipes/glm-5-3-flash-4x6000-jj-mtp3/recipe.yaml +++ b/recipes/glm-5-3-flash-4x6000-jj-mtp3/recipe.yaml @@ -95,3 +95,4 @@ provenance: - 'https://github.com/local-inference-lab/rtx6kpro/blob/master/benchmarks/karmic-kraken-serving.md' - 'https://github.com/local-inference-lab/rtx6kpro/blob/master/models/glm-5.3-flash-community-r35.md' notes: 'Saved r35 numbers from the Karmic Kraken comparison table (same-box Max-Q +6000 conditions). Launch argv transcribed from the r35 community deployment page (docker run, TP4/DCP1, GPU_MEM 0.93, fp8_ds_mla KV).' +max_context_len: 1048576