Upgrade to 0.11.1 newest vllm commit (#3982)
### What this PR does / why we need it?
adapt vllm-ascend main branch with vllm releases/v0.11.1
fix `forward context not set` in test_vlm.py caused by:
https://github.com/vllm-project/vllm/pull/23207
fix import `cdiv round` failed caused by:
https://github.com/vllm-project/vllm/pull/27188
fix import `init_cached_hf_modules` failed caused by:
https://github.com/vllm-project/vllm/pull/27567
adapt triton kernel `fused_recurrent_gated_delta_rule_fwd_kernel` caused
by: https://github.com/vllm-project/vllm/pull/27654
- remove unused code in sigmoid_gating.py
- `class FusedRecurrentFunction` , `fused_recurrent_gated_delta_rule`,
`fused_recurrent_gated_delta_rule_fwd`
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
CI
- vLLM version: v0.11.0
- vLLM main:
83f478bb19
Signed-off-by: 22dimensions <waitingwind@foxmail.com>
This commit is contained in:
@@ -8,6 +8,9 @@ from vllm.config import CacheConfig, ModelConfig, ParallelConfig, VllmConfig
|
||||
from tests.ut.base import TestBase
|
||||
from vllm_ascend.utils import vllm_version_is
|
||||
|
||||
init_cached_hf_modules_path = "vllm.utils.init_cached_hf_modules" if vllm_version_is(
|
||||
"0.11.0") else "vllm.utils.import_utils.init_cached_hf_modules"
|
||||
|
||||
|
||||
class TestNPUWorker(TestBase):
|
||||
|
||||
@@ -53,7 +56,7 @@ class TestNPUWorker(TestBase):
|
||||
@patch("vllm_ascend.worker.worker_v1.init_ascend_config")
|
||||
@patch("vllm_ascend.worker.worker_v1.init_ascend_soc_version")
|
||||
@patch("vllm_ascend.worker.worker_v1.try_register_lib")
|
||||
@patch("vllm.utils.init_cached_hf_modules")
|
||||
@patch(init_cached_hf_modules_path)
|
||||
@patch("vllm_ascend.worker.worker_v1.NPUWorker._init_profiler")
|
||||
def test_init_npu_worker_normal_case(
|
||||
self,
|
||||
@@ -115,7 +118,7 @@ class TestNPUWorker(TestBase):
|
||||
@patch("vllm_ascend.worker.worker_v1.init_ascend_config")
|
||||
@patch("vllm_ascend.worker.worker_v1.init_ascend_soc_version")
|
||||
@patch("vllm_ascend.worker.worker_v1.try_register_lib")
|
||||
@patch("vllm.utils.init_cached_hf_modules")
|
||||
@patch(init_cached_hf_modules_path)
|
||||
@patch("vllm_ascend.worker.worker_v1.NPUWorker._init_profiler")
|
||||
def test_init_npu_worker_with_trust_remote_code(
|
||||
self,
|
||||
@@ -160,7 +163,7 @@ class TestNPUWorker(TestBase):
|
||||
@patch("vllm_ascend.worker.worker_v1.init_ascend_config")
|
||||
@patch("vllm_ascend.worker.worker_v1.init_ascend_soc_version")
|
||||
@patch("vllm_ascend.worker.worker_v1.try_register_lib")
|
||||
@patch("vllm.utils.init_cached_hf_modules")
|
||||
@patch(init_cached_hf_modules_path)
|
||||
@patch("vllm_ascend.worker.worker_v1.NPUWorker._init_profiler")
|
||||
def test_init_npu_worker_with_custom_cache_dtype(
|
||||
self,
|
||||
|
||||
Reference in New Issue
Block a user