EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

cleanup ascend config (#5296)

Browse Source 
1. refresh additional config doc
2. move kv config logic to platform.
3. improve `dump_config` init logic and rename it to `dump_config_path`
this change is user impacted. dump_config is changed from dict to
string.
4. correct `enable_async_exponential` type
5. remove useless `chunked_prefill_for_mla`

- vLLM version: release/v0.13.0
- vLLM main:
ad32e3e19c

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2025-12-26 14:07:37 +08:00
committed by GitHub
parent adaa89a7a5
commit 29d2fe653d
11 changed files with 98 additions and 118 deletions
Download Patch File Download Diff File Expand all files Collapse all files

64
vllm_ascend/ascend_config.py
View File

@@ -14,43 +14,11 @@
# See the License for the specific language governing permissions and
# limitations under the License.
from typing import Optional
from uuid import uuid4
from vllm.logger import logger
from vllm.triton_utils import HAS_TRITON
def check_kv_extra_config(vllm_config):
def _check(name: str, config: dict):
tp_key = "tp_size"
dp_key = "dp_size"
if tp_key in config:
config_tp = config[tp_key]
vllm_tp = vllm_config.parallel_config.tensor_parallel_size
if config_tp != vllm_tp:
raise ValueError(
f"KV transfer '{name}' config has a conflicting tensor parallel size. "
f"Expected {vllm_tp}, but got {config_tp}.")
if dp_key in config:
config_dp = config[dp_key]
vllm_dp = vllm_config.parallel_config.data_parallel_size
if config_dp != vllm_dp:
raise ValueError(
f"KV transfer '{name}' config has a conflicting data parallel size. "
f"Expected {vllm_dp}, but got {config_dp}.")
if vllm_config.kv_transfer_config.is_kv_producer:
_check(
"prefill",
vllm_config.kv_transfer_config.get_from_extra_config(
"prefill", {}))
if vllm_config.kv_transfer_config.is_kv_consumer:
_check(
"decode",
vllm_config.kv_transfer_config.get_from_extra_config("decode", {}))
class AscendConfig:
"""
Configuration Object for additional_config from vllm.configs.
@@ -74,8 +42,7 @@ class AscendConfig:
finegrained_tp_config, vllm_config)
# Dump / PrecisionDebugger configuration
dump_config_path = additional_config.get("dump_config", None)
self.dump_config = DumpConfig(dump_config_path)
self.dump_config_path = additional_config.get("dump_config_path", None)
weight_prefetch_config = additional_config.get(
"weight_prefetch_config", {})
@@ -96,8 +63,6 @@ class AscendConfig:
self.gate_eplb = additional_config.get("gate_eplb", False)
self.num_wait_worker_iterations = additional_config.get(
"num_wait_worker_iterations", 30)
self.chunked_prefill_for_mla = additional_config.get(
"chunked_prefill_for_mla", False)
self.enable_shared_expert_dp = additional_config.get(
"enable_shared_expert_dp",
False) and vllm_config.parallel_config.enable_expert_parallel
@@ -114,9 +79,6 @@ class AscendConfig:
self.enable_cpu_binding = additional_config.get(
"enable_cpu_binding", False)
if vllm_config.kv_transfer_config is not None:
check_kv_extra_config(vllm_config)
self.pd_tp_ratio = 1
self.pd_head_ratio = 1
self.num_head_replica = 1
@@ -156,16 +118,8 @@ class AscendConfig:
# npu_fused_infer_attention_score performs better on all scenarios.
self.pa_shape_list = additional_config.get("pa_shape_list", [])
kv_cfg = vllm_config.kv_transfer_config
if kv_cfg is not None and not getattr(kv_cfg, "_engine_id_patched",
False):
kv_cfg.engine_id = f"{kv_cfg.engine_id}-{uuid4().hex}"
kv_cfg._engine_id_patched = True
self.enable_async_exponential = additional_config.get(
"enable_async_exponential", 0)
if self.enable_async_exponential not in (0, 1):
raise AssertionError(
"Enable async exponential can only be set to 0 or 1.")
self.enable_async_exponential = bool(
additional_config.get("enable_async_exponential", False))
class FinegrainedTPConfig:
@@ -274,18 +228,6 @@ class XliteGraphConfig:
)
class DumpConfig:
"""
Configuration object for dump/PrecisionDebugger settings.
"""
def __init__(self, dump_config_path: Optional[str] = None):
# enable_dump is True when dump_cfg exists and config_path is not empty
self.enable_dump: bool = bool(dump_config_path)
# Path to msprobe config json; may be None.
self.config_path: Optional[str] = dump_config_path
class WeightPrefetchConfig:
"""
Configuration Object for weight_prefetch_config from additional_config

18
vllm_ascend/platform.py
View File

@@ -18,6 +18,7 @@
import gc
import os
from typing import TYPE_CHECKING, Optional, Tuple
from uuid import uuid4
import torch
from vllm.logger import logger
@@ -30,12 +31,11 @@ from vllm_ascend.ascend_config import init_ascend_config
from vllm_ascend.utils import refresh_block_size
# isort: off
from vllm_ascend.utils import (ASCEND_QUANTIZATION_METHOD,
COMPRESSED_TENSORS_METHOD, AscendDeviceType,
enable_sp, get_ascend_device_type, is_vl_model,
update_aclgraph_sizes,
update_cudagraph_capture_sizes,
update_default_aclgraph_sizes)
from vllm_ascend.utils import (
ASCEND_QUANTIZATION_METHOD, COMPRESSED_TENSORS_METHOD, AscendDeviceType,
enable_sp, get_ascend_device_type, is_vl_model, update_aclgraph_sizes,
update_cudagraph_capture_sizes, update_default_aclgraph_sizes,
check_kv_extra_config)
if TYPE_CHECKING:
from vllm.config import ModelConfig, VllmConfig
@@ -152,6 +152,12 @@ class NPUPlatform(Platform):
# initialize ascend config from vllm additional_config
ascend_config = init_ascend_config(vllm_config)
if vllm_config.kv_transfer_config is not None:
check_kv_extra_config(vllm_config)
if not getattr(vllm_config.kv_transfer_config,
"_engine_id_patched", False):
vllm_config.kv_transfer_config.engine_id = f"{vllm_config.kv_transfer_config.engine_id}-{uuid4().hex}"
vllm_config.kv_transfer_config._engine_id_patched = True
from vllm.config import CompilationMode # noqa: E402
compilation_config = vllm_config.compilation_config

2
vllm_ascend/sample/sampler.py
View File

@@ -83,7 +83,7 @@ class AscendTopKTopPSampler(TopKTopPSampler):
logits_to_return = logits.log_softmax(dim=-1, dtype=torch.float32)
probs = logits.softmax(dim=-1, dtype=torch.float32)
if get_ascend_config().enable_async_exponential == 1:
if get_ascend_config().enable_async_exponential:
# Add synchronize to prevent synchronize error.
self.async_event.synchronize()
return probs.div_(self.q).argmax(dim=-1).view(-1), logits_to_return

31
vllm_ascend/utils.py
View File

@@ -1084,3 +1084,34 @@ def dispose_layer(layer: Any):
def replace_layer(original_layer: Any, new_layer: Any):
original_layer.__class__ = new_layer.__class__
original_layer.__dict__ = new_layer.__dict__
def check_kv_extra_config(vllm_config):
def _check(name: str, config: dict):
tp_key = "tp_size"
dp_key = "dp_size"
if tp_key in config:
config_tp = config[tp_key]
vllm_tp = vllm_config.parallel_config.tensor_parallel_size
if config_tp != vllm_tp:
raise ValueError(
f"KV transfer '{name}' config has a conflicting tensor parallel size. "
f"Expected {vllm_tp}, but got {config_tp}.")
if dp_key in config:
config_dp = config[dp_key]
vllm_dp = vllm_config.parallel_config.data_parallel_size
if config_dp != vllm_dp:
raise ValueError(
f"KV transfer '{name}' config has a conflicting data parallel size. "
f"Expected {vllm_dp}, but got {config_dp}.")
if vllm_config.kv_transfer_config.is_kv_producer:
_check(
"prefill",
vllm_config.kv_transfer_config.get_from_extra_config(
"prefill", {}))
if vllm_config.kv_transfer_config.is_kv_consumer:
_check(
"decode",
vllm_config.kv_transfer_config.get_from_extra_config("decode", {}))

24
vllm_ascend/worker/model_runner_v1.py
View File

@@ -216,13 +216,12 @@ class NPUModelRunner(GPUModelRunner):
self.ascend_config = get_ascend_config()
set_weight_prefetch_method(self.ascend_config.weight_prefetch_config)
# Dump / PrecisionDebugger configuration now comes from AscendConfig
dump_cfg = self.ascend_config.dump_config
self.dump_enable = dump_cfg.enable_dump
dump_cfg = self.ascend_config.dump_config_path
self.debugger = None
if self.dump_enable:
if dump_cfg is not None:
if self.model_config.enforce_eager:
from msprobe.pytorch import PrecisionDebugger
self.debugger = PrecisionDebugger(dump_cfg.config_path)
self.debugger = PrecisionDebugger(dump_cfg)
else:
raise RuntimeError(
"Dumping/debugging only works in eager mode.")
@@ -1388,9 +1387,7 @@ class NPUModelRunner(GPUModelRunner):
self.eplb_updator.take_update_info_from_eplb_process()
# prevent debugger is None
need_dump = self.dump_enable and self.debugger is not None
if need_dump:
assert self.debugger is not None
if self.debugger is not None:
dbg_cfg = getattr(self.debugger, "config", None)
dump_level = str(
getattr(dbg_cfg, "level",
@@ -1407,7 +1404,7 @@ class NPUModelRunner(GPUModelRunner):
aclgraph_runtime_mode, batch_descriptor = \
self.cudagraph_dispatcher.dispatch(num_tokens=num_input_tokens, uniform_decode=uniform_decode, has_lora=has_lora)
if self.ascend_config.enable_async_exponential != 0:
if self.ascend_config.enable_async_exponential:
self.sampler.do_async_exponential(
b_s=logits_indices.shape[0],
head_dim=self.model_config.get_vocab_size(),
@@ -1457,8 +1454,7 @@ class NPUModelRunner(GPUModelRunner):
if not broadcast_pp_output:
hidden_states.kv_connector_output = kv_connector_output
self.kv_connector_output = kv_connector_output
if need_dump:
assert self.debugger is not None
if self.debugger is not None:
self.debugger.stop()
self.debugger.step()
return hidden_states
@@ -1472,8 +1468,7 @@ class NPUModelRunner(GPUModelRunner):
hidden_states,
scheduler_output.total_num_scheduled_tokens,
num_scheduled_tokens_np)
if need_dump:
assert self.debugger is not None
if self.debugger is not None:
self.debugger.stop()
self.debugger.step()
return pool_output
@@ -1529,7 +1524,6 @@ class NPUModelRunner(GPUModelRunner):
output.kv_connector_output = kv_connector_output
return output
need_dump = self.dump_enable and self.debugger is not None
# Unpack ephemeral state.
(
scheduler_output,
@@ -1628,13 +1622,13 @@ class NPUModelRunner(GPUModelRunner):
if self.dynamic_eplb:
self.eplb_updator.forward_end()
if not self.use_async_scheduling:
if need_dump:
if self.debugger is not None:
assert self.debugger is not None
self.debugger.stop()
self.debugger.step()
return model_runner_output
if need_dump:
if self.debugger is not None:
assert self.debugger is not None
self.debugger.stop()
self.debugger.step()