Revert "[Test Fix] Fix/update test_run_compressed (#970)"

This reverts commit a343ff0.
vllm-project · Jan 14, 2025 · b987d75 · b987d75
1 parent a343ff0
commit b987d75
Show file tree

Hide file tree

Showing 11 changed files with 45 additions and 299 deletions.
diff --git a/tests/llmcompressor/transformers/compression/decompression_configs/fp8_dynamic.yaml b/tests/llmcompressor/transformers/compression/decompression_configs/fp8_dynamic.yaml
diff --git a/tests/llmcompressor/transformers/compression/decompression_configs/w4a16.yaml b/tests/llmcompressor/transformers/compression/decompression_configs/w4a16.yaml
diff --git a/tests/llmcompressor/transformers/compression/decompression_configs/w8a16_dense.yaml b/tests/llmcompressor/transformers/compression/decompression_configs/w8a16_dense.yaml
diff --git a/tests/llmcompressor/transformers/compression/decompression_configs/w8a8.yaml b/tests/llmcompressor/transformers/compression/decompression_configs/w8a8.yaml
diff --git a/tests/llmcompressor/transformers/compression/run_compressed_configs/fp8_dynamic.yaml b/tests/llmcompressor/transformers/compression/run_compressed_configs/fp8_dynamic.yaml
@@ -1,4 +1,4 @@
 cadence: "commit"
 test_type: "regression"
-compressed_model_stub: nm-testing/TinyLlama-1.1B-Chat-v1.0-FP8-Dynamic-compressed
-uncompressed_model_stub: nm-testing/TinyLlama-1.1B-Chat-v1.0-FP8-Dynamic-uncompressed
+model_stub: "nm-testing/tinyllama-fp8-dynamic-compressed"
+empty_model: "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T" 
diff --git a/tests/llmcompressor/transformers/compression/run_compressed_configs/w4a16.yaml b/tests/llmcompressor/transformers/compression/run_compressed_configs/w4a16.yaml
@@ -1,4 +1,4 @@
 cadence: "commit"
 test_type: "regression"
-compressed_model_stub: nm-testing/TinyLlama-1.1B-Chat-v1.0-W4A16-G128-compressed
-uncompressed_model_stub: nm-testing/TinyLlama-1.1B-Chat-v1.0-W4A16-G128-uncompressed
+model_stub: "nm-testing/tinyllama-w4a16-compressed"
+empty_model: "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T"
diff --git a/tests/llmcompressor/transformers/compression/run_compressed_configs/w8a16.yaml b/tests/llmcompressor/transformers/compression/run_compressed_configs/w8a16.yaml
diff --git a/tests/llmcompressor/transformers/compression/run_compressed_configs/w8a16_dense.yaml b/tests/llmcompressor/transformers/compression/run_compressed_configs/w8a16_dense.yaml
@@ -0,0 +1,4 @@
+cadence: "commit"
+test_type: "regression"
+model_stub: "nm-testing/tinyllama-w8a16-dense"
+empty_model: "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T"
diff --git a/tests/llmcompressor/transformers/compression/run_compressed_configs/w8a8.yaml b/tests/llmcompressor/transformers/compression/run_compressed_configs/w8a8.yaml
@@ -1,4 +1,4 @@
 cadence: "commit"
 test_type: "regression"
-compressed_model_stub: nm-testing/TinyLlama-1.1B-Chat-v1.0-W8A8-Dynamic-Per-Token-compressed
-uncompressed_model_stub: nm-testing/TinyLlama-1.1B-Chat-v1.0-W8A8-Dynamic-Per-Token-uncompressed
+model_stub: "nm-testing/tinyllama-w8a8-compressed"
+empty_model: "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T"
diff --git a/tests/llmcompressor/transformers/compression/test_decompress.py b/tests/llmcompressor/transformers/compression/test_decompress.py