Update config.yaml (#11208)

* update config.yaml

* fix

* minor

* style

python/llm/dev/benchmark/all-in-one/config.yaml

@@ -12,12 +12,11 @@ in_out_pairs:
   - '32-32'
   - '1024-128'
 test_api:
-  - "transformer_int4_gpu"                # on Intel GPU, transformer-like API, (qtype=int4)
-  # - "transformer_int4_gpu_win"            # on Intel GPU for Windows, transformer-like API, (qtype=int4)
-  # - "transformer_int4_fp16_gpu"           # on Intel GPU, transformer-like API, (qtype=int4), (dtype=fp16)
+  - "transformer_int4_fp16_gpu"             # on Intel GPU, transformer-like API, (qtype=int4), (dtype=fp16)
   # - "transformer_int4_fp16_gpu_win"       # on Intel GPU for Windows, transformer-like API, (qtype=int4), (dtype=fp16)
+  # - "transformer_int4_gpu"                # on Intel GPU, transformer-like API, (qtype=int4), (dtype=fp32)
+  # - "transformer_int4_gpu_win"            # on Intel GPU for Windows, transformer-like API, (qtype=int4), (dtype=fp32)
   # - "transformer_int4_loadlowbit_gpu_win" # on Intel GPU for Windows, transformer-like API, (qtype=int4), use load_low_bit API. Please make sure you have used the save.py to save the converted low bit model
-  # - "ipex_fp16_gpu"                       # on Intel GPU, use native transformers API, (dtype=fp16)
   # - "bigdl_fp16_gpu"                      # on Intel GPU, use ipex-llm transformers API, (dtype=fp16), (qtype=fp16)
   # - "optimize_model_gpu"                  # on Intel GPU, can optimize any pytorch models include transformer model
   # - "deepspeed_optimize_model_gpu"        # on Intel GPU, deepspeed autotp inference
@@ -35,8 +34,8 @@ test_api:
   # - "deepspeed_transformer_int4_cpu"      # on Intel CPU, deepspeed autotp inference
   # - "transformer_int4_fp16_lookahead_gpu" # on Intel GPU, transformer-like API, with lookahead, (qtype=int4), (dtype=fp16)
 cpu_embedding: False # whether put embedding to CPU
-streaming: False # whether output in streaming way (only avaiable now for gpu win related test_api)
-use_fp16_torch_dtype: True # whether use fp16 for non-linear layer (only avaiable now for "pipeline_parallel_gpu" test_api)
-n_gpu: 2 # number of GPUs to use (only avaiable now for "pipeline_parallel_gpu" test_api)
+streaming: False # whether output in streaming way (only available now for gpu win related test_api)
+use_fp16_torch_dtype: True # whether use fp16 for non-linear layer (only available now for "pipeline_parallel_gpu" test_api)
+n_gpu: 2 # number of GPUs to use (only available now for "pipeline_parallel_gpu" test_api)
 lookahead: 3
 max_matching_ngram_size: 2