[Executorch][perf-ci] Fix perf ci

.github/workflows/android-perf.yml

@@ -222,6 +222,7 @@ jobs:
                       --preq_mode 8da4w_output_8da8w \
                       --preq_group_size 32 \
                       --max_seq_length 2048 \
+                      --max_context_length 2048 \
                       --output_name "${OUT_ET_MODEL_NAME}.pte" \
                       -kv \
                       -d fp32 \
@@ -253,6 +254,7 @@ jobs:
                       --xnnpack-extended-ops \
                       -d fp32 \
                       --max_seq_length 2048 \
+                      --max_context_length 2048 \
                       --output_name "${OUT_ET_MODEL_NAME}.pte" \
                       --metadata '{"get_bos_id":128000, "get_eos_ids":[128009, 128001]}'
                     ls -lh "${OUT_ET_MODEL_NAME}.pte"

.github/workflows/apple-perf.yml

@@ -233,6 +233,7 @@ jobs:
                 --preq_mode 8da4w_output_8da8w \
                 --preq_group_size 32 \
                 --max_seq_length 2048 \
+                --max_context_length 2048 \
                 --output_name "${OUT_ET_MODEL_NAME}.pte" \
                 -kv \
                 -d fp32 \
@@ -264,6 +265,7 @@ jobs:
                 --xnnpack-extended-ops \
                 -d fp32 \
                 --max_seq_length 2048 \
+                --max_context_length 2048 \
                 --output_name "${OUT_ET_MODEL_NAME}.pte" \
                 --metadata '{"get_bos_id":128000, "get_eos_ids":[128009, 128001]}'
               ls -lh "${OUT_ET_MODEL_NAME}.pte"

examples/demo-apps/android/LlamaDemo/docs/delegates/xnnpack_README.md

@@ -56,14 +56,14 @@ In this demo app, we support text-only inference with up-to-date Llama models an
 Meta has released prequantized INT4 SpinQuant Llama 3.2 models that ExecuTorch supports on the XNNPACK backend.
 * Export Llama model and generate .pte file as below:
 ```
-python -m examples.models.llama.export_llama --model "llama3_2" --checkpoint <path-to-your-checkpoint.pth> --params <path-to-your-params.json> -kv --use_sdpa_with_kv_cache -X -d fp32 --xnnpack-extended-ops --preq_mode 8da4w_output_8da8w --preq_group_size 32 --max_seq_length 2048 --preq_embedding_quantize 8,0 --use_spin_quant native --metadata '{"get_bos_id":128000, "get_eos_ids":[128009, 128001]}' --output_name "llama3_2_spinquant.pte"
+python -m examples.models.llama.export_llama --model "llama3_2" --checkpoint <path-to-your-checkpoint.pth> --params <path-to-your-params.json> -kv --use_sdpa_with_kv_cache -X -d fp32 --xnnpack-extended-ops --preq_mode 8da4w_output_8da8w --preq_group_size 32 --max_seq_length 2048 --max_context_length 2048 --preq_embedding_quantize 8,0 --use_spin_quant native --metadata '{"get_bos_id":128000, "get_eos_ids":[128009, 128001]}' --output_name "llama3_2_spinquant.pte"
 ```
 
 ### For Llama 3.2 1B and 3B QAT+LoRA models
 Meta has released prequantized INT4 QAT+LoRA Llama 3.2 models that ExecuTorch supports on the XNNPACK backend.
 * Export Llama model and generate .pte file as below:
 ```
-python -m examples.models.llama.export_llama --model "llama3_2" --checkpoint <path-to-your-checkpoint.pth> --params <path-to-your-params.json> -qat -lora 16 -kv --use_sdpa_with_kv_cache -X -d fp32 --xnnpack-extended-ops --preq_mode 8da4w_output_8da8w --preq_group_size 32 --max_seq_length 2048 --preq_embedding_quantize 8,0 --metadata '{"get_bos_id":128000, "get_eos_ids":[128009, 128001]}' --output_name "llama3_2_qat_lora.pte"
+python -m examples.models.llama.export_llama --model "llama3_2" --checkpoint <path-to-your-checkpoint.pth> --params <path-to-your-params.json> -qat -lora 16 -kv --use_sdpa_with_kv_cache -X -d fp32 --xnnpack-extended-ops --preq_mode 8da4w_output_8da8w --preq_group_size 32 --max_seq_length 2048 --max_context_length 2048--preq_embedding_quantize 8,0 --metadata '{"get_bos_id":128000, "get_eos_ids":[128009, 128001]}' --output_name "llama3_2_qat_lora.pte"
 ```
 
 ### For Llama 3.2 1B and 3B BF16 models
@@ -87,7 +87,7 @@ To safeguard your application, you can use our Llama Guard models for prompt cla
 * We prepared this model using the following command
 
 ```
-python -m examples.models.llama.export_llama --checkpoint <path-to-pruned-llama-guard-1b-checkpoint.pth> --params <path-to-your-params.json> -d fp32 -kv --use_sdpa_with_kv_cache --quantization_mode 8da4w --group_size 256 --xnnpack --max_seq_length 8193 --embedding-quantize 4,32 --metadata '{"get_bos_id":128000, "get_eos_ids":[128009, 128001]}' --output_prune_map <path-to-your-llama_guard-pruned-layers-map.json> --output_name="llama_guard_3_1b_pruned_xnnpack.pte"
+python -m examples.models.llama.export_llama --checkpoint <path-to-pruned-llama-guard-1b-checkpoint.pth> --params <path-to-your-params.json> -d fp32 -kv --use_sdpa_with_kv_cache --quantization_mode 8da4w --group_size 256 --xnnpack --max_seq_length 8193 --max_context_length 8193 --embedding-quantize 4,32 --metadata '{"get_bos_id":128000, "get_eos_ids":[128009, 128001]}' --output_prune_map <path-to-your-llama_guard-pruned-layers-map.json> --output_name="llama_guard_3_1b_pruned_xnnpack.pte"
 ```
 
 

examples/demo-apps/apple_ios/LLaMA/docs/delegates/xnnpack_README.md

@@ -51,14 +51,14 @@ sh examples/models/llama/install_requirements.sh
 Meta has released prequantized INT4 SpinQuant Llama 3.2 models that ExecuTorch supports on the XNNPACK backend.
 * Export Llama model and generate .pte file as below:
 ```
-python -m examples.models.llama.export_llama --model "llama3_2" --checkpoint <path-to-your-checkpoint.pth> --params <path-to-your-params.json> -kv --use_sdpa_with_kv_cache -X -d fp32 --xnnpack-extended-ops --preq_mode 8da4w_output_8da8w --preq_group_size 32 --max_seq_length 2048 --preq_embedding_quantize 8,0 --use_spin_quant native --metadata '{"get_bos_id":128000, "get_eos_ids":[128009, 128001]}' --output_name "llama3_2_spinquant.pte"
+python -m examples.models.llama.export_llama --model "llama3_2" --checkpoint <path-to-your-checkpoint.pth> --params <path-to-your-params.json> -kv --use_sdpa_with_kv_cache -X -d fp32 --xnnpack-extended-ops --preq_mode 8da4w_output_8da8w --preq_group_size 32 --max_seq_length 2048 --max_context_length 2048 --preq_embedding_quantize 8,0 --use_spin_quant native --metadata '{"get_bos_id":128000, "get_eos_ids":[128009, 128001]}' --output_name "llama3_2_spinquant.pte"
 ```
 
 ### For Llama 3.2 1B and 3B QAT+LoRA models
 Meta has released prequantized INT4 QAT+LoRA Llama 3.2 models that ExecuTorch supports on the XNNPACK backend.
 * Export Llama model and generate .pte file as below:
 ```
-python -m examples.models.llama.export_llama --model "llama3_2" --checkpoint <path-to-your-checkpoint.pth> --params <path-to-your-params.json> -qat -lora 16 -kv --use_sdpa_with_kv_cache -X -d fp32 --xnnpack-extended-ops --preq_mode 8da4w_output_8da8w --preq_group_size 32 --max_seq_length 2048 --preq_embedding_quantize 8,0 --metadata '{"get_bos_id":128000, "get_eos_ids":[128009, 128001]}' --output_name "llama3_2_qat_lora.pte"
+python -m examples.models.llama.export_llama --model "llama3_2" --checkpoint <path-to-your-checkpoint.pth> --params <path-to-your-params.json> -qat -lora 16 -kv --use_sdpa_with_kv_cache -X -d fp32 --xnnpack-extended-ops --preq_mode 8da4w_output_8da8w --preq_group_size 32 --max_seq_length 2048 --max_context_length 2048 --preq_embedding_quantize 8,0 --metadata '{"get_bos_id":128000, "get_eos_ids":[128009, 128001]}' --output_name "llama3_2_qat_lora.pte"
 ```
 
 ### For Llama 3.2 1B and 3B BF16 models

examples/models/llama/README.md

@@ -199,6 +199,7 @@ python -m examples.models.llama.export_llama \
    --preq_mode 8da4w_output_8da8w \
    --preq_group_size 32 \
    --max_seq_length 2048 \
+   --max_context_length 2048 \
    --output_name "llama3_2.pte" \
    -kv \
    -d fp32 \
@@ -230,6 +231,7 @@ python -m examples.models.llama.export_llama \
    --xnnpack-extended-ops \
    -d fp32 \
    --max_seq_length 2048 \
+   --max_context_length 2048 \
    --output_name "llama3_2.pte" \
    --metadata '{"get_bos_id":128000, "get_eos_ids":[128009, 128001]}'
 ```
@@ -397,6 +399,7 @@ python -m examples.models.llama.eval_llama \
 	-kv \
 	-d <checkpoint dtype> \
 	--max_seq_len <max sequence length> \
+	--max_context_len <max context length> \
 	--limit <number of samples>
 ```
 
@@ -411,6 +414,7 @@ python -m examples.models.llama.eval_llama \
 	--tasks mmlu \
 	--num_fewshot 5 \
 	--max_seq_len <max sequence length>
+	--max_context_len <max context length>
 ```
 
 See [Llama utils page](./UTILS.md) page for more advanced use-cases such as fine-tuning and running smaller models for educational purposes, and quick iteration and verification.