Modify arc nightly perf to fp16 (#11275)

* change api * move to pr mode and remove the build * add batch4 yaml and remove the bigcode * remove batch4 * revert the starcode * remove the exclude * revert --------- Co-authored-by: Yishuo Wang <[email protected]>
intel-analytics · Jun 17, 2024 · bca5cbd · bca5cbd
1 parent a2a5890
commit bca5cbd
Show file tree

Hide file tree

Showing 4 changed files with 4 additions and 4 deletions.
diff --git a/python/llm/test/benchmark/arc-perf-test-batch2.yaml b/python/llm/test/benchmark/arc-perf-test-batch2.yaml
@@ -29,7 +29,7 @@ in_out_pairs:
   - '1024-128'
   - '2048-256'
 test_api:
-  - "transformer_int4_gpu"  # on Intel GPU
+  - "transformer_int4_fp16_gpu"  # on Intel GPU
 cpu_embedding: False # whether put embedding to CPU (only avaiable now for gpu win related test_api)
 exclude:
   - 'bigcode/starcoder-15.5b-4bit:2048'

diff --git a/python/llm/test/benchmark/arc-perf-test.yaml b/python/llm/test/benchmark/arc-perf-test.yaml
@@ -29,7 +29,7 @@ in_out_pairs:
   - '1024-128'
   - '2048-256'
 test_api:
-  - "transformer_int4_gpu"  # on Intel GPU
+  - "transformer_int4_fp16_gpu"  # on Intel GPU
 cpu_embedding: False # whether put embedding to CPU (only avaiable now for gpu win related test_api)
 exclude:
 #  - 'fnlp/moss-moon-003-sft-4bit:1024'

diff --git a/python/llm/test/benchmark/arc-perf-transformers-437-batch2.yaml b/python/llm/test/benchmark/arc-perf-transformers-437-batch2.yaml
@@ -15,5 +15,5 @@ in_out_pairs:
   - '1024-128'
   - '2048-256'
 test_api:
-  - "transformer_int4_gpu"  # on Intel GPU
+  - "transformer_int4_fp16_gpu"  # on Intel GPU
 cpu_embedding: False # whether put embedding to CPU (only avaiable now for gpu win related test_api)
diff --git a/python/llm/test/benchmark/arc-perf-transformers-437.yaml b/python/llm/test/benchmark/arc-perf-transformers-437.yaml
@@ -15,5 +15,5 @@ in_out_pairs:
   - '1024-128'
   - '2048-256'
 test_api:
-  - "transformer_int4_gpu"  # on Intel GPU
+  - "transformer_int4_fp16_gpu"  # on Intel GPU
 cpu_embedding: False # whether put embedding to CPU (only avaiable now for gpu win related test_api)