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

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()