[Main2Main] Upgrade vllm commit to 0109 (#5752)
### What this PR does / why we need it?
Upgrade vllm commit to 0109 (bde38c11df0ea066a740efe9b77fff5418be45df)
1. remove `init_cached_hf_modules ` due to
https://github.com/vllm-project/vllm/pull/31786
2. fix spec_decode e2e test due to
https://github.com/vllm-project/vllm/pull/29821 break
3. fix `vllm.v1.attention.backends.utils` duo to
https://github.com/vllm-project/vllm/pull/31891
4. fix `self.seq_lens - query_lens` on same device due to
https://github.com/vllm-project/vllm/pull/31773
5. skip model_runner_v2 e2e test due to `'_OpNamespace' '_C' object has
no attribute 'get_cuda_view_from_cpu_tensor'`
- vLLM version: v0.13.0
- vLLM main:
2f4e6548ef
Signed-off-by: hfadzxy <starmoon_zhang@163.com>
This commit is contained in:
@@ -305,15 +305,16 @@ def test_rmsnorm_quant_fusion(
|
||||
|
||||
vllm_config = VllmConfig(model_config=ModelConfig(dtype=dtype))
|
||||
|
||||
update_environment_variables({
|
||||
"RANK": "0",
|
||||
"LOCAL_RANK": "0",
|
||||
"WORLD_SIZE": "1",
|
||||
"MASTER_ADDR": "localhost",
|
||||
"MASTER_PORT": "12345",
|
||||
})
|
||||
init_distributed_environment()
|
||||
ensure_model_parallel_initialized(1, 1)
|
||||
with vllm.config.set_current_vllm_config(vllm_config):
|
||||
update_environment_variables({
|
||||
"RANK": "0",
|
||||
"LOCAL_RANK": "0",
|
||||
"WORLD_SIZE": "1",
|
||||
"MASTER_ADDR": "localhost",
|
||||
"MASTER_PORT": "12345",
|
||||
})
|
||||
init_distributed_environment()
|
||||
ensure_model_parallel_initialized(1, 1)
|
||||
|
||||
with vllm.config.set_current_vllm_config(vllm_config):
|
||||
with set_ascend_forward_context(None, vllm_config):
|
||||
|
||||
Reference in New Issue
Block a user