anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[NPU] upgrade to v0.29.0 (#7433)

Browse Source 
Signed-off-by: Weiming Liao <liaowm5@gmail.com>
This commit is contained in:
Weiming Liao authored and GitHub committed 2026-09-12 04:14:42 +00:00
1 parent 9ef9fc442a
commit b3ba67d71e
6 files changed
+50 -26
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docker/Dockerfile.npu
+1 -1
View File
@@ -1,5 +1,5 @@
ARG VLLM_ASCEND_IMAGE=quay.io/atlas-ci/vllm-ascend
ARG VLLM_ASCEND_VERSION=v0.28.0
ARG VLLM_ASCEND_VERSION=v0.29.0
ARG VLLM_ASCEND_DEVICE_SUFFIX=
FROM ${VLLM_ASCEND_IMAGE}:${VLLM_ASCEND_VERSION}${VLLM_ASCEND_DEVICE_SUFFIX}
docker/Dockerfile.npu.ci
+1 -1
View File
@@ -1,5 +1,5 @@
ARG VLLM_ASCEND_IMAGE=quay.io/atlas-ci/vllm-ascend
ARG VLLM_ASCEND_VERSION=v0.28.0
ARG VLLM_ASCEND_VERSION=v0.29.0
ARG VLLM_ASCEND_DEVICE_SUFFIX=
FROM ${VLLM_ASCEND_IMAGE}:${VLLM_ASCEND_VERSION}${VLLM_ASCEND_DEVICE_SUFFIX}
docs/getting_started/installation/npu/npu.inc.md
+11 -11
View File
@@ -10,25 +10,25 @@ The recommended way to use vLLM-Omni on NPU is through the vLLM-Ascend pre-built
=== "A2"
```bash
export IMAGE=quay.io/atlas-ci/vllm-ascend:v0.28.0
export IMAGE=quay.io/atlas-ci/vllm-ascend:v0.29.0
```
=== "A3"
```bash
export IMAGE=quay.io/atlas-ci/vllm-ascend:v0.28.0-a3
export IMAGE=quay.io/atlas-ci/vllm-ascend:v0.29.0-a3
```
=== "A5"
```bash
export IMAGE=quay.io/atlas-ci/vllm-ascend:v0.28.0-a5
export IMAGE=quay.io/atlas-ci/vllm-ascend:v0.29.0-a5
```
=== "310P (Experimental)"
```bash
export IMAGE=quay.io/atlas-ci/vllm-ascend:v0.28.0-310p
export IMAGE=quay.io/atlas-ci/vllm-ascend:v0.29.0-310p
```
```bash
@@ -53,7 +53,7 @@ docker run --rm \
# Inside the container, install vLLM-Omni from source
cd /vllm-workspace
git clone -b v0.28.0 https://github.com/vllm-project/vllm-omni.git
git clone -b v0.29.0rc1 https://github.com/vllm-project/vllm-omni.git
cd vllm-omni
pip install -v -e . --no-build-isolation
# or VLLM_OMNI_TARGET_DEVICE=npu pip install -v -e .
@@ -71,10 +71,10 @@ We are keeping [issue #886](https://github.com/vllm-project/vllm-omni/issues/886
# --8<-- [start:installation-main]
You can also install vLLM-Omni from the latest main branch if you want to use the latest features or bug fixes. Use the aligned vLLM-Ascend v0.28.0 image described above, and check [issue #886](https://github.com/vllm-project/vllm-omni/issues/886) for the status of the latest vLLM-Omni commit on NPU.
You can also install vLLM-Omni from the latest main branch if you want to use the latest features or bug fixes. Use the aligned vLLM-Ascend v0.29.0 image described above, and check [issue #886](https://github.com/vllm-project/vllm-omni/issues/886) for the status of the latest vLLM-Omni commit on NPU.
```bash
# Inside the vLLM-Ascend v0.28.0 container, install vLLM-Omni from main
# Inside the vLLM-Ascend v0.29.0 container, install vLLM-Omni from main
cd /vllm-workspace
git clone https://github.com/vllm-project/vllm-omni.git
cd vllm-omni
@@ -103,7 +103,7 @@ Here's an example deployment command that has been verified on 4 x NPUs:
=== "A2"
```bash
export IMAGE=quay.io/ascend/vllm-omni:v0.28.0
export IMAGE=quay.io/ascend/vllm-omni:v0.29.0
docker run --rm \
--name vllm-omni-a2 \
--shm-size=64g \
@@ -127,7 +127,7 @@ Here's an example deployment command that has been verified on 4 x NPUs:
=== "A3"
```bash
export IMAGE=quay.io/ascend/vllm-omni:v0.28.0-a3
export IMAGE=quay.io/ascend/vllm-omni:v0.29.0-a3
docker run --rm \
--name vllm-omni-a3 \
--shm-size=64g \
@@ -151,7 +151,7 @@ Here's an example deployment command that has been verified on 4 x NPUs:
=== "A5"
```bash
export IMAGE=quay.io/ascend/vllm-omni:v0.28.0-a5
export IMAGE=quay.io/ascend/vllm-omni:v0.29.0-a5
docker run --rm \
--name vllm-omni-a5 \
--shm-size=64g \
@@ -175,7 +175,7 @@ Here's an example deployment command that has been verified on 4 x NPUs:
=== "310P (Experimental)"
```bash
export IMAGE=quay.io/ascend/vllm-omni:v0.28.0-310p
export IMAGE=quay.io/ascend/vllm-omni:v0.29.0-310p
docker run --rm \
--name vllm-omni-310p \
--shm-size=64g \
vllm_omni/platforms/npu/worker/npu_ar_model_runner.py
+7 -1
View File
@@ -334,6 +334,8 @@ class NPUARModelRunner(OmniNPUModelRunner, OmniConnectorModelRunnerMixin, Duplex
if not isinstance(info, dict):
return None
val = info.get("omni_final_stage_id")
if val is None:
return None
try:
return int(val)
except (TypeError, ValueError):
@@ -512,7 +514,7 @@ class NPUARModelRunner(OmniNPUModelRunner, OmniConnectorModelRunnerMixin, Duplex
# returns True. before returning early here we call
# dummy run to ensure coordinate_batch_across_dp
# is called into to avoid out of sync issues.
self._dummy_run(1)
self._dummy_run(1, skip_gdn_state_update=True)
kv_ids = self.kv_extracted_req_ids
self.kv_extracted_req_ids = None
@@ -1035,6 +1037,8 @@ class NPUARModelRunner(OmniNPUModelRunner, OmniConnectorModelRunnerMixin, Duplex
propose_draft_token_ids(sampler_output.sampled_token_ids)
(
num_nans_in_logits,
num_nans_device,
logprobs_lists,
valid_sampled_token_ids,
prompt_logprobs_dict,
@@ -1278,6 +1282,7 @@ class NPUARModelRunner(OmniNPUModelRunner, OmniConnectorModelRunnerMixin, Duplex
kv_connector_output=kv_connector_output,
ec_connector_output=ec_connector_output if self.supports_mm_inputs else None,
cudagraph_stats=cudagraph_stats,
num_nans_in_logits=num_nans_in_logits,
)
model_runner_output.kv_extracted_req_ids = kv_extracted_req_ids
model_runner_output.routed_experts = routed_experts_lists
@@ -1318,6 +1323,7 @@ class NPUARModelRunner(OmniNPUModelRunner, OmniConnectorModelRunnerMixin, Duplex
invalid_req_indices=invalid_req_indices,
async_output_copy_stream=self.async_output_copy_stream,
vocab_size=self.input_batch.vocab_size,
num_nans=num_nans_device,
)
self.input_batch.set_async_sampled_token_ids(
async_output.sampled_token_ids_cpu,
vllm_omni/platforms/npu/worker/npu_generation_model_runner.py
+15 -6
View File
@@ -166,7 +166,7 @@ class NPUGenerationModelRunner(OmniNPUModelRunner, OmniConnectorModelRunnerMixin
# returns True. before returning early here we call
# dummy run to ensure coordinate_batch_across_dp
# is called into to avoid out of sync issues.
self._dummy_run(1)
self._dummy_run(1, skip_gdn_state_update=True)
if not has_kv_transfer_group():
# Return empty ModelRunnerOutput if no work to do.
return self.attach_omni_connector_output(EMPTY_MODEL_RUNNER_OUTPUT)
@@ -636,6 +636,7 @@ class NPUGenerationModelRunner(OmniNPUModelRunner, OmniConnectorModelRunnerMixin
profile_seq_lens: int | None = None,
profile_cpp: bool = False,
randomize_inputs: bool = False,
skip_gdn_state_update: bool = False,
) -> tuple[torch.Tensor, torch.Tensor]:
# only support eager mode and piecewise graph now
assert cudagraph_runtime_mode is None or cudagraph_runtime_mode.is_valid_runtime_mode()
@@ -768,7 +769,10 @@ class NPUGenerationModelRunner(OmniNPUModelRunner, OmniConnectorModelRunnerMixin
self.query_start_loc.np[1 : num_reqs_padded + 1] = cum_num_tokens
self.query_start_loc.copy_to_gpu()
if self._has_gdn:
self.gdn_query_start_loc.np[1 : num_reqs_padded + 1] = cum_num_tokens
if skip_gdn_state_update:
self.gdn_query_start_loc.np.fill(0)
else:
self.gdn_query_start_loc.np[1 : num_reqs_padded + 1] = cum_num_tokens
self.gdn_query_start_loc.copy_to_gpu()
if not profile_cpp:
@@ -786,6 +790,12 @@ class NPUGenerationModelRunner(OmniNPUModelRunner, OmniConnectorModelRunnerMixin
# rows as well so device-side metadata does not see stale block ids.
self.input_batch.block_table.commit_block_table(num_reqs_padded)
# Invalidate slots before backends copy metadata for dummy execution.
if not is_graph_capturing:
for kv_cache_gid in range(len(self.kv_cache_config.kv_cache_groups)):
blk_table = self.input_batch.block_table[kv_cache_gid]
blk_table.slot_mapping.gpu.fill_(-1)
pad_attn = cudagraph_runtime_mode == CUDAGraphMode.FULL
attn_metadata, _ = self._build_attention_metadata(
num_tokens=num_tokens_unpadded,
@@ -796,11 +806,10 @@ class NPUGenerationModelRunner(OmniNPUModelRunner, OmniConnectorModelRunnerMixin
ubatch_slices=ubatch_slices_padded if pad_attn else ubatch_slices,
for_cudagraph_capture=is_graph_capturing,
num_scheduled_tokens_np=num_scheduled_tokens,
cudagraph_runtime_mode=cudagraph_runtime_mode,
batch_descriptor=batch_desc,
skip_gdn_state_update=skip_gdn_state_update,
)
if not is_graph_capturing:
for kv_cache_gid in range(len(self.kv_cache_config.kv_cache_groups)):
blk_table = self.input_batch.block_table[kv_cache_gid]
blk_table.slot_mapping.gpu.fill_(-1)
with self.maybe_dummy_run_with_lora(
self.lora_config,
vllm_omni/platforms/npu/worker/npu_model_runner.py
+15 -6
View File
@@ -1,5 +1,5 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
from functools import partial
from typing import Any
@@ -126,6 +126,7 @@ class OmniNPUModelRunner(OmniGPUModelRunner, NPUModelRunner):
profile_seq_lens: int | None = None,
profile_cpp: bool = False,
randomize_inputs: bool = False,
skip_gdn_state_update: bool = False,
) -> tuple[torch.Tensor, torch.Tensor]:
# only support eager mode and piecewise graph now
assert cudagraph_runtime_mode is None or cudagraph_runtime_mode.is_valid_runtime_mode()
@@ -257,7 +258,10 @@ class OmniNPUModelRunner(OmniGPUModelRunner, NPUModelRunner):
self.query_start_loc.np[1 : num_reqs_padded + 1] = cum_num_tokens
self.query_start_loc.copy_to_gpu()
if self._has_gdn:
self.gdn_query_start_loc.np[1 : num_reqs_padded + 1] = cum_num_tokens
if skip_gdn_state_update:
self.gdn_query_start_loc.np.fill(0)
else:
self.gdn_query_start_loc.np[1 : num_reqs_padded + 1] = cum_num_tokens
self.gdn_query_start_loc.copy_to_gpu()
if not profile_cpp:
@@ -275,6 +279,12 @@ class OmniNPUModelRunner(OmniGPUModelRunner, NPUModelRunner):
# rows as well so device-side metadata does not see stale block ids.
self.input_batch.block_table.commit_block_table(num_reqs_padded)
# Invalidate slots before backends copy metadata for dummy execution.
if not is_graph_capturing:
for kv_cache_gid in range(len(self.kv_cache_config.kv_cache_groups)):
blk_table = self.input_batch.block_table[kv_cache_gid]
blk_table.slot_mapping.gpu.fill_(-1)
pad_attn = cudagraph_runtime_mode == CUDAGraphMode.FULL
attn_metadata, _ = self._build_attention_metadata(
num_tokens=num_tokens_unpadded,
@@ -285,11 +295,10 @@ class OmniNPUModelRunner(OmniGPUModelRunner, NPUModelRunner):
ubatch_slices=ubatch_slices_padded if pad_attn else ubatch_slices,
for_cudagraph_capture=is_graph_capturing,
num_scheduled_tokens_np=num_scheduled_tokens,
cudagraph_runtime_mode=cudagraph_runtime_mode,
batch_descriptor=batch_desc,
skip_gdn_state_update=skip_gdn_state_update,
)
if not is_graph_capturing:
for kv_cache_gid in range(len(self.kv_cache_config.kv_cache_groups)):
blk_table = self.input_batch.block_table[kv_cache_gid]
blk_table.slot_mapping.gpu.fill_(-1)
with self.maybe_dummy_run_with_lora(
self.lora_config,