Merge pull request #301 from adithyaJRunpod/feature/tuned-configs

Add tuned configs, CON-239
2026-06-11 14:26:00 -05:00
parent 105c125698 0a0ccfcb60
commit d3a962c33b
2 changed files with 20 additions and 0 deletions
@@ -0,0 +1,10 @@
+model: meta-llama/Llama-3.1-8B-Instruct
+gpu-memory-utilization: 0.95
+max-model-len: 8192
+dtype: auto
+trust-remote-code: true
+quantization: fp8
+kv-cache-dtype: fp8
+enforce-eager: false
+enable-prefix-caching: true
+speculative-config: '{"model":"RedHatAI/Llama-3.1-8B-Instruct-speculator.eagle3","method":"eagle3","num_speculative_tokens":3}'
@@ -0,0 +1,10 @@
+model: Qwen/Qwen3-8B
+gpu-memory-utilization: 0.95
+max-model-len: 8192
+dtype: auto
+trust-remote-code: true
+quantization: fp8
+kv-cache-dtype: fp8
+enforce-eager: false
+enable-prefix-caching: true
+speculative-config: '{"model":"RedHatAI/Qwen3-8B-speculator.eagle3","method":"eagle3","num_speculative_tokens":3}'