[Mini-VLLM] Remove the ROCm device path, debug routes and arch-gated tests
- Delete csrc/rocm, hipify, the _rocm_C extension and the setup.py rocm target path; drop the rocm requirement files - Delete the aiter, rdna3, skinny-gemm and ROCm fused-MoE kernel modules and retarget the linear kernel registries away from them - Reduce platforms/rocm.py to the GCN architecture predicates that live code still imports, and delete the RocmPlatform class and plugin - Drop the VLLM_SERVER_DEV_MODE debug surface: reset, collective_rpc, server_info and sleep routes plus the log_error_stack flag - Delete lm-format-enforcer, lark and otel-semantic-conventions-ai pins; the live server process maps none of them - Delete tests that only build architectures this fork no longer registers, and test directories left without any test file - Restore the tests/v1/kv_connector mock helpers that scheduler tests import at module level Co-authored-by: Hinata <hinata@idihore.id> Signed-off-by: MOVZX <movzx@yahoo.com>
This commit is contained in:
@@ -1,31 +0,0 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
|
||||
import pytest
|
||||
|
||||
from vllm.entrypoints.llm import LLM
|
||||
from vllm.sampling_params import SamplingParams
|
||||
|
||||
|
||||
@pytest.mark.parametrize("model", ["distilbert/distilgpt2"])
|
||||
def test_computed_prefix_blocks(model: str):
|
||||
# This test checks if the engine generates completions both with and
|
||||
# without optional detokenization, that detokenization includes text
|
||||
# and no-detokenization doesn't, and that both completions have the same
|
||||
# token_ids.
|
||||
prompt = (
|
||||
"You are a helpful assistant. How do I build a car from cardboard and "
|
||||
"paper clips? Is there an easy to follow video tutorial available "
|
||||
"online for free?"
|
||||
)
|
||||
|
||||
llm = LLM(model=model)
|
||||
sampling_params = SamplingParams(max_tokens=10, temperature=0.0, detokenize=False)
|
||||
|
||||
outputs_no_detokenization = llm.generate(prompt, sampling_params)[0].outputs[0]
|
||||
sampling_params.detokenize = True
|
||||
outputs_with_detokenization = llm.generate(prompt, sampling_params)[0].outputs[0]
|
||||
|
||||
assert outputs_no_detokenization.text == ""
|
||||
assert outputs_with_detokenization.text != ""
|
||||
assert outputs_no_detokenization.token_ids == outputs_with_detokenization.token_ids
|
||||
Reference in New Issue
Block a user