| 1 | #!/bin/bash |
| 2 | |
| 3 | set -euo pipefail |
| 4 | |
| 5 | test_suite="${1:-}" |
| 6 | |
| 7 | if [[ -z "${test_suite}" ]]; then |
| 8 | echo "Usage: $0 <example|w8a8-fp8-linear|v1|server|quantization|compressed-tensors-fp8|graph>" >&2 |
| 9 | exit 1 |
| 10 | fi |
| 11 | |
| 12 | case "${test_suite}" in |
| 13 | example) |
| 14 | pip install tblib==3.1.0 |
| 15 | |
| 16 | python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager |
| 17 | python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 -O3 -cc.cudagraph_mode=NONE |
| 18 | python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager -tp 2 --distributed-executor-backend mp |
| 19 | python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager --attention-backend=TRITON_ATTN |
| 20 | python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager --quantization fp8_per_tensor |
| 21 | python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager --kv-cache-dtype fp8 |
| 22 | python3 examples/basic/offline_inference/generate.py --model nvidia/Llama-3.1-8B-Instruct-FP8 --block-size 64 --enforce-eager --quantization modelopt --kv-cache-dtype fp8 --attention-backend TRITON_ATTN --max-model-len 4096 |
| 23 | python3 examples/basic/offline_inference/generate.py --model superjob/Qwen3-4B-Instruct-2507-GPTQ-Int4 --block-size 64 --enforce-eager --max-model-len 8192 |
| 24 | python3 examples/basic/offline_inference/generate.py --model TheBloke/TinyLlama-1.1B-Chat-v0.3-AWQ --block-size 64 --enforce-eager |
| 25 | python3 examples/basic/offline_inference/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2 |
| 26 | python3 examples/basic/offline_inference/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2 --enable-expert-parallel |
| 27 | python3 examples/basic/offline_inference/generate.py --model superjob/Qwen3-4B-Instruct-2507-GPTQ-Int4 --max-model-len 8192 |
| 28 | ;; |
| 29 | w8a8-fp8-linear) |
| 30 | python3 examples/basic/offline_inference/generate.py --linear-backend xpu --model RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8 --enforce-eager --max-model-len 4096 |
| 31 | python3 examples/basic/offline_inference/generate.py --linear-backend torch --model RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8 --enforce-eager --max-model-len 4096 |
| 32 | python3 examples/basic/offline_inference/generate.py --linear-backend xpu --model neuralmagic/Llama-3.2-1B-Instruct-FP8-dynamic --enforce-eager --max-model-len 4096 |
| 33 | python3 examples/basic/offline_inference/generate.py --linear-backend xpu --model meta-llama/Llama-3.2-1B-Instruct --quantization fp8_per_tensor --enforce-eager --max-model-len 4096 |
| 34 | python3 examples/basic/offline_inference/generate.py --linear-backend torch --model meta-llama/Llama-3.2-1B-Instruct --quantization fp8_per_tensor --enforce-eager --max-model-len 4096 |
| 35 | ;; |
| 36 | v1) |
| 37 | cd tests |
| 38 | |
| 39 | pytest -v -s v1/core --ignore=v1/core/test_reset_prefix_cache_e2e.py --ignore=v1/core/test_scheduler_e2e.py |
| 40 | pytest -v -s v1/engine --ignore=v1/engine/test_output_processor.py --ignore=v1/engine/test_core_engine_actor_manager.py |
| 41 | pytest -v -s v1/sample --ignore=v1/sample/test_logprobs.py --ignore=v1/sample/test_logprobs_e2e.py -k "not test_topk_only and not test_topp_only and not test_topk_and_topp" |
| 42 | pytest -v -s v1/worker --ignore=v1/worker/test_gpu_model_runner.py --ignore=v1/worker/test_worker_memory_snapshot.py |
| 43 | pytest -v -s v1/structured_output |
| 44 | pytest -v -s v1/test_serial_utils.py |
| 45 | pytest -v -s v1/e2e/general/test_correctness_sliding_window.py |
| 46 | pytest -v -s v1/spec_decode --ignore=v1/spec_decode/test_max_len.py --ignore=v1/spec_decode/test_speculators_eagle3.py --ignore=v1/spec_decode/test_acceptance_length.py --ignore=v1/spec_decode/test_speculators_correctness.py --deselect=tests/v1/spec_decode/test_mtp.py::test_glm_mtp_defers_lm_head |
| 47 | pytest -v -s v1/kv_connector/unit --ignore=v1/kv_connector/unit/test_multi_connector.py --ignore=v1/kv_connector/unit/test_example_connector.py --ignore=v1/kv_connector/unit/test_lmcache_integration.py --ignore=v1/kv_connector/unit/test_hf3fs_client.py --ignore=v1/kv_connector/unit/test_hf3fs_connector.py --ignore=v1/kv_connector/unit/test_hf3fs_metadata_server.py --ignore=v1/kv_connector/unit/test_offloading_connector.py --ignore=v1/kv_connector/unit/test_nixl_connector_hma.py --deselect=tests/v1/kv_connector/unit/test_nixl_connector.py::test_abort_timeout_on_prefiller[ray] |
| 48 | ;; |
| 49 | server) |
| 50 | pip install av |
| 51 | cd tests |
| 52 | |
| 53 | pytest -v -s entrypoints/multimodal/openai/chat_completion/test_audio_in_video.py |
| 54 | pytest -v -s benchmarks/test_serve_cli.py |
| 55 | ;; |
| 56 | quantization) |
| 57 | cd tests |
| 58 | |
| 59 | pytest -v -s quantization/test_auto_round.py |
| 60 | pytest -v -s quantization/test_online.py --deselect=tests/quantization/test_online.py::test_online_quantization_loads_real_weights |
| 61 | ;; |
| 62 | compressed-tensors-fp8) |
| 63 | cd tests |
| 64 | |
| 65 | pytest -v -s quantization/test_compressed_tensors.py::test_compressed_tensors_fp8 |
| 66 | ;; |
| 67 | graph) |
| 68 | python3 examples/basic/offline_inference/generate.py --model Qwen/Qwen3-0.6B |
| 69 | python3 examples/basic/offline_inference/generate.py --model Qwen/Qwen3-0.6B --kv-cache-dtype fp8 |
| 70 | python3 examples/basic/offline_inference/generate.py --model INCModel/Qwen3-30B-A3B-Instruct-2507-MXFP4-CT-AutoRound --max-model-len 4096 |
| 71 | ;; |
| 72 | *) |
| 73 | echo "Unknown Intel test suite: ${test_suite}" >&2 |
| 74 | exit 1 |
| 75 | ;; |
| 76 | esac |