[EPLB][CI] EPLB add aclgraph and redundant expert ci (#5625)
### What this PR does / why we need it? EPLB currently does not have CI related to aclgraph and redundancy experts; this PR adds them. release on #5529 ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? Tested the use cases to be added in this PR. PASSED ====================================================== warnings summary ========================================================== <frozen importlib._bootstrap>:241 <frozen importlib._bootstrap>:241: DeprecationWarning: builtin type SwigPyPacked has no __module__ attribute <frozen importlib._bootstrap>:241 <frozen importlib._bootstrap>:241: DeprecationWarning: builtin type SwigPyObject has no __module__ attribute -- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html ====================================================== 1 passed, 2 warnings in 272.24s (0:04:32) ===================================================== - vLLM version: v0.13.0 - vLLM main: https://github.com/vllm-project/vllm/commit/8be6432bdaf6275664d857b1e5e9bf8ed1ce299e Signed-off-by: shenchuxiaofugui <1311027364@qq.com>
This commit is contained in:
1 parent
264cc254cc
commit
b69db4ce55
1 file changed
+6
-4
@@ -79,10 +79,11 @@ def test_qwen3_moe_distributed_aiv_tp2():
|
||||
async def test_qwen3_moe_w8a8_distributed_tp2_ep_dynamic_eplb():
|
||||
model = "vllm-ascend/Qwen3-30B-A3B-W8A8"
|
||||
port = get_open_port()
|
||||
compilation_config = json.dumps({"cudagraph_capture_sizes": [8]})
|
||||
server_args = [
|
||||
"--max_model_len", "8192", "--tensor_parallel_size", "2",
|
||||
"--enable_expert_parallel", "--quantization", "ascend", "--port",
|
||||
str(port), "--enforce_eager"
|
||||
str(port), "--compilation-config", compilation_config
|
||||
]
|
||||
env_dict = {"HCCL_BUFFSIZE": "1024"}
|
||||
with RemoteOpenAIServer(model,
|
||||
@@ -93,7 +94,7 @@ async def test_qwen3_moe_w8a8_distributed_tp2_ep_dynamic_eplb():
|
||||
client = server.get_async_client()
|
||||
batch = await client.completions.create(model=model,
|
||||
prompt="What is deeplearning?",
|
||||
max_tokens=300,
|
||||
max_tokens=400,
|
||||
temperature=0,
|
||||
top_p=1.0,
|
||||
n=1)
|
||||
@@ -106,7 +107,8 @@ async def test_qwen3_moe_w8a8_distributed_tp2_ep_dynamic_eplb():
|
||||
additional_config = {
|
||||
"dynamic_eplb": True,
|
||||
"num_iterations_eplb_update": 100,
|
||||
"num_wait_worker_iterations": 20
|
||||
"num_wait_worker_iterations": 20,
|
||||
"num_redundant_experts": 2
|
||||
}
|
||||
server_args.extend(["--additional-config", json.dumps(additional_config)])
|
||||
with RemoteOpenAIServer(model,
|
||||
@@ -117,7 +119,7 @@ async def test_qwen3_moe_w8a8_distributed_tp2_ep_dynamic_eplb():
|
||||
client = server.get_async_client()
|
||||
batch = await client.completions.create(model=model,
|
||||
prompt="What is deeplearning?",
|
||||
max_tokens=300,
|
||||
max_tokens=400,
|
||||
temperature=0,
|
||||
top_p=1.0,
|
||||
n=1)
|
||||
|
||||
Reference in new issue
Block a user