[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:
@@ -1,2 +0,0 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
@@ -1,17 +0,0 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
|
||||
import pytest
|
||||
|
||||
from vllm.platforms import current_platform
|
||||
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def require_rocm_cdna4() -> None:
|
||||
if not current_platform.is_rocm():
|
||||
pytest.skip("requires ROCm")
|
||||
|
||||
from vllm.platforms.rocm import on_gfx950
|
||||
|
||||
if not on_gfx950():
|
||||
pytest.skip("requires CDNA4")
|
||||
@@ -1,41 +0,0 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
"""Shared BF16 baselines for the quantization comparison tests.
|
||||
|
||||
Several tests here quantize the same model and compare against an
|
||||
unquantized run of it. Computing that reference once per session avoids
|
||||
booting an identical engine for every quantization scheme under test.
|
||||
|
||||
Only the outputs are cached; each engine is still torn down as usual, so
|
||||
tests keep the isolation ``VllmRunner.__exit__`` provides.
|
||||
"""
|
||||
|
||||
import pytest
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def quant_baseline_logprobs(vllm_runner):
|
||||
"""Greedy logprobs for an unquantized model, computed once per config."""
|
||||
cache: dict = {}
|
||||
|
||||
def baseline(
|
||||
model: str,
|
||||
prompts: list[str],
|
||||
*,
|
||||
max_model_len: int,
|
||||
max_tokens: int,
|
||||
num_logprobs: int,
|
||||
):
|
||||
key = (model, max_model_len, max_tokens, num_logprobs, tuple(prompts))
|
||||
if key not in cache:
|
||||
with vllm_runner(
|
||||
model,
|
||||
max_model_len=max_model_len,
|
||||
enforce_eager=True,
|
||||
) as vllm_model:
|
||||
cache[key] = vllm_model.generate_greedy_logprobs(
|
||||
prompts, max_tokens, num_logprobs
|
||||
)
|
||||
return cache[key]
|
||||
|
||||
return baseline
|
||||
Reference in New Issue
Block a user