[AMD] register 3 tests to stage-b-test-1-gpu-large-amd (batch-6) (#28736)
This commit is contained in:
@@ -17,11 +17,12 @@ from sglang.srt.layers.attention.flashattention_backend import (
|
|||||||
normal_decode_set_metadata,
|
normal_decode_set_metadata,
|
||||||
)
|
)
|
||||||
from sglang.srt.mem_cache.swa_memory_pool import SWAKVPool
|
from sglang.srt.mem_cache.swa_memory_pool import SWAKVPool
|
||||||
from sglang.test.ci.ci_register import register_cuda_ci
|
from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci
|
||||||
from sglang.test.test_utils import CustomTestCase
|
from sglang.test.test_utils import CustomTestCase
|
||||||
|
|
||||||
# Register this test for CUDA CI in base-b (fast attention/kernel tests)
|
# Register this test for CUDA CI in base-b (fast attention/kernel tests)
|
||||||
register_cuda_ci(est_time=11, stage="base-b", runner_config="1-gpu-large")
|
register_cuda_ci(est_time=11, stage="base-b", runner_config="1-gpu-large")
|
||||||
|
register_amd_ci(est_time=17, suite="stage-b-test-1-gpu-large-amd")
|
||||||
|
|
||||||
|
|
||||||
def reference_normal_decode_set_metadata(
|
def reference_normal_decode_set_metadata(
|
||||||
|
|||||||
@@ -23,7 +23,7 @@ import requests
|
|||||||
import torch
|
import torch
|
||||||
|
|
||||||
from sglang.srt.utils import kill_process_tree
|
from sglang.srt.utils import kill_process_tree
|
||||||
from sglang.test.ci.ci_register import register_cuda_ci
|
from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci
|
||||||
from sglang.test.runners import SRTRunner
|
from sglang.test.runners import SRTRunner
|
||||||
from sglang.test.test_utils import (
|
from sglang.test.test_utils import (
|
||||||
DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
|
DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
|
||||||
@@ -39,6 +39,10 @@ register_cuda_ci(
|
|||||||
stage="base-b",
|
stage="base-b",
|
||||||
runner_config="1-gpu-large",
|
runner_config="1-gpu-large",
|
||||||
)
|
)
|
||||||
|
register_amd_ci(
|
||||||
|
est_time=730,
|
||||||
|
suite="stage-b-test-1-gpu-large-amd",
|
||||||
|
)
|
||||||
|
|
||||||
PROMPTS = [
|
PROMPTS = [
|
||||||
"SGL is a",
|
"SGL is a",
|
||||||
|
|||||||
@@ -8,10 +8,11 @@ from sglang.srt.layers.attention.trtllm_mha_backend import TRTLLMHAAttnBackend
|
|||||||
from sglang.srt.mem_cache.base_swa_memory_pool import BaseSWAKVPool
|
from sglang.srt.mem_cache.base_swa_memory_pool import BaseSWAKVPool
|
||||||
from sglang.srt.mem_cache.swa_memory_pool import SWAKVPool
|
from sglang.srt.mem_cache.swa_memory_pool import SWAKVPool
|
||||||
from sglang.srt.speculative.spec_info import SpeculativeAlgorithm
|
from sglang.srt.speculative.spec_info import SpeculativeAlgorithm
|
||||||
from sglang.test.ci.ci_register import register_cuda_ci
|
from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci
|
||||||
from sglang.test.test_utils import CustomTestCase
|
from sglang.test.test_utils import CustomTestCase
|
||||||
|
|
||||||
register_cuda_ci(est_time=5, stage="base-b", runner_config="1-gpu-large")
|
register_cuda_ci(est_time=5, stage="base-b", runner_config="1-gpu-large")
|
||||||
|
register_amd_ci(est_time=8, suite="stage-b-test-1-gpu-large-amd")
|
||||||
|
|
||||||
_RESOLVERS = (
|
_RESOLVERS = (
|
||||||
("trtllm_mha", TRTLLMHAAttnBackend._resolve_swa_kv_pool, SWAKVPool),
|
("trtllm_mha", TRTLLMHAAttnBackend._resolve_swa_kv_pool, SWAKVPool),
|
||||||
|
|||||||
Reference in New Issue
Block a user