comments'

vllm-project · Dec 13, 2024 · 2f84c1a · 2f84c1a
1 parent 0076cd9
commit 2f84c1a
Show file tree

Hide file tree

Showing 5 changed files with 336 additions and 312 deletions.
diff --git a/tests/llmcompressor/test_kv_cache.py b/tests/llmcompressor/test_kv_cache.py
diff --git a/tests/llmcompressor/transformers/kv_cache/configs/gptq_kv_cache/gptq_kv_cache.yaml b/tests/llmcompressor/transformers/kv_cache/configs/gptq_kv_cache/gptq_kv_cache.yaml
@@ -0,0 +1,2 @@
+cadence: "commit"
+test_type: "regression"
diff --git a/tests/llmcompressor/transformers/kv_cache/configs/kv_cache/phi3.yaml b/tests/llmcompressor/transformers/kv_cache/configs/kv_cache/phi3.yaml
@@ -0,0 +1,3 @@
+cadence: "commit"
+test_type: "regression"
+model: "microsoft/Phi-3-mini-4k-instruct"
diff --git a/tests/llmcompressor/transformers/kv_cache/configs/kv_cache/tiny_llama.yaml b/tests/llmcompressor/transformers/kv_cache/configs/kv_cache/tiny_llama.yaml
@@ -0,0 +1,3 @@
+cadence: "commit"
+test_type: "regression"
+model: "TinyLlama/TinyLlama-1.1B-Chat-v1.0"