supoort 310p moe #1327
Closed
supoort 310p moe #1327
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Angazenn
force-pushed
the
310p
branch
2 times, most recently
from
9c587ce to
0792d0d
Compare
Signed-off-by: angazenn <[email protected]>
This was referenced Jun 20, 2025
Yikun
added a commit
that referenced
this pull request
Jun 21, 2025
…1333) ### What this PR does / why we need it? Add initial experimental support for Ascend 310P, this patch squash below PR into one to help validation: - #914 - #1318 - #1327 ### Does this PR introduce _any_ user-facing change? User can run vLLM on Altlas 300I DUO series ### How was this patch tested? CI passed with: - E2E image build for 310P - CI test on A2 with e2e test and longterm test - Unit test missing because need a real 310P image to have the test, will add in a separate PR later. - Manually e2e test: - Qwen2.5-7b-instruct, Qwen2.5-0.5b, Qwen3-0.6B, Qwen3-4B, Qwen3-8B: #914 (comment) - Pangu MGoE 72B The patch has been tested locally on Ascend 310P hardware to ensure that the changes do not break existing functionality and that the new features work as intended. #### ENV information CANN, NNAL version: 8.1.RC1 > [!IMPORTANT] > PTA 2.5.1 version >= torch_npu-2.5.1.post1.dev20250528 to support NZ format and calling NNAL operators on 310P #### Code example ##### Build vllm-ascend from source code ```shell # download source code as vllm-ascend cd vllm-ascend export SOC_VERSION=Ascend310P3 pip install -v -e . cd .. ``` ##### Run offline inference ```python from vllm import LLM, SamplingParams prompts = ["水的沸点是100摄氏度吗？请回答是或者否。", "若腋下体温为38摄氏度，请问这人是否发烧？请回答是或者否。", "水的沸点是100摄氏度吗？请回答是或者否。", "若腋下体温为38摄氏度，请问这人是否发烧？请回答是或者否。"] # Create a sampling params object. sampling_params = SamplingParams(temperature=0.0, top_p=0.95, max_tokens=10) # Create an LLM. llm = LLM( model="Qwen/Qwen2.5-7B-Instruct", max_model_len=4096, max_num_seqs=4, dtype="float16", # IMPORTANT cause some ATB ops cannot support bf16 on 310P disable_custom_all_reduce=True, trust_remote_code=True, tensor_parallel_size=2, compilation_config={"custom_ops":['none', "+rms_norm", "+rotary_embedding"]}, ) # Generate texts from the prompts. outputs = llm.generate(prompts, sampling_params) for output in outputs: prompt = output.prompt generated_text = output.outputs[0].text print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}") ``` --------- Signed-off-by: Vincent Yuan <[email protected]> Signed-off-by: Yikun Jiang <[email protected]> Signed-off-by: angazenn <[email protected]> Co-authored-by: Vincent Yuan <[email protected]> Co-authored-by: angazenn <[email protected]> Co-authored-by: wangxiyuan <[email protected]> Co-authored-by: leo-pony <[email protected]> Co-authored-by: shen-shanshan <[email protected]>
|
Many thanks for your contributions, I squashed all 310P related commits with your co-author: #1333 |
chopper0126
pushed a commit
to chopper0126/vllm-ascend
that referenced
this pull request
Oct 16, 2025
…llm-project#1333) ### What this PR does / why we need it? Add initial experimental support for Ascend 310P, this patch squash below PR into one to help validation: - vllm-project#914 - vllm-project#1318 - vllm-project#1327 ### Does this PR introduce _any_ user-facing change? User can run vLLM on Altlas 300I DUO series ### How was this patch tested? CI passed with: - E2E image build for 310P - CI test on A2 with e2e test and longterm test - Unit test missing because need a real 310P image to have the test, will add in a separate PR later. - Manually e2e test: - Qwen2.5-7b-instruct, Qwen2.5-0.5b, Qwen3-0.6B, Qwen3-4B, Qwen3-8B: vllm-project#914 (comment) - Pangu MGoE 72B The patch has been tested locally on Ascend 310P hardware to ensure that the changes do not break existing functionality and that the new features work as intended. #### ENV information CANN, NNAL version: 8.1.RC1 > [!IMPORTANT] > PTA 2.5.1 version >= torch_npu-2.5.1.post1.dev20250528 to support NZ format and calling NNAL operators on 310P #### Code example ##### Build vllm-ascend from source code ```shell # download source code as vllm-ascend cd vllm-ascend export SOC_VERSION=Ascend310P3 pip install -v -e . cd .. ``` ##### Run offline inference ```python from vllm import LLM, SamplingParams prompts = ["水的沸点是100摄氏度吗？请回答是或者否。", "若腋下体温为38摄氏度，请问这人是否发烧？请回答是或者否。", "水的沸点是100摄氏度吗？请回答是或者否。", "若腋下体温为38摄氏度，请问这人是否发烧？请回答是或者否。"] # Create a sampling params object. sampling_params = SamplingParams(temperature=0.0, top_p=0.95, max_tokens=10) # Create an LLM. llm = LLM( model="Qwen/Qwen2.5-7B-Instruct", max_model_len=4096, max_num_seqs=4, dtype="float16", # IMPORTANT cause some ATB ops cannot support bf16 on 310P disable_custom_all_reduce=True, trust_remote_code=True, tensor_parallel_size=2, compilation_config={"custom_ops":['none', "+rms_norm", "+rotary_embedding"]}, ) # Generate texts from the prompts. outputs = llm.generate(prompts, sampling_params) for output in outputs: prompt = output.prompt generated_text = output.outputs[0].text print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}") ``` --------- Signed-off-by: Vincent Yuan <[email protected]> Signed-off-by: Yikun Jiang <[email protected]> Signed-off-by: angazenn <[email protected]> Co-authored-by: Vincent Yuan <[email protected]> Co-authored-by: angazenn <[email protected]> Co-authored-by: wangxiyuan <[email protected]> Co-authored-by: leo-pony <[email protected]> Co-authored-by: shen-shanshan <[email protected]>
Angazenn
pushed a commit
to Angazenn/vllm-ascend
that referenced
this pull request
Oct 21, 2025
…llm-project#1333) ### What this PR does / why we need it? Add initial experimental support for Ascend 310P, this patch squash below PR into one to help validation: - vllm-project#914 - vllm-project#1318 - vllm-project#1327 ### Does this PR introduce _any_ user-facing change? User can run vLLM on Altlas 300I DUO series ### How was this patch tested? CI passed with: - E2E image build for 310P - CI test on A2 with e2e test and longterm test - Unit test missing because need a real 310P image to have the test, will add in a separate PR later. - Manually e2e test: - Qwen2.5-7b-instruct, Qwen2.5-0.5b, Qwen3-0.6B, Qwen3-4B, Qwen3-8B: vllm-project#914 (comment) - Pangu MGoE 72B The patch has been tested locally on Ascend 310P hardware to ensure that the changes do not break existing functionality and that the new features work as intended. #### ENV information CANN, NNAL version: 8.1.RC1 > [!IMPORTANT] > PTA 2.5.1 version >= torch_npu-2.5.1.post1.dev20250528 to support NZ format and calling NNAL operators on 310P #### Code example ##### Build vllm-ascend from source code ```shell # download source code as vllm-ascend cd vllm-ascend export SOC_VERSION=Ascend310P3 pip install -v -e . cd .. ``` ##### Run offline inference ```python from vllm import LLM, SamplingParams prompts = ["水的沸点是100摄氏度吗？请回答是或者否。", "若腋下体温为38摄氏度，请问这人是否发烧？请回答是或者否。", "水的沸点是100摄氏度吗？请回答是或者否。", "若腋下体温为38摄氏度，请问这人是否发烧？请回答是或者否。"] # Create a sampling params object. sampling_params = SamplingParams(temperature=0.0, top_p=0.95, max_tokens=10) # Create an LLM. llm = LLM( model="Qwen/Qwen2.5-7B-Instruct", max_model_len=4096, max_num_seqs=4, dtype="float16", # IMPORTANT cause some ATB ops cannot support bf16 on 310P disable_custom_all_reduce=True, trust_remote_code=True, tensor_parallel_size=2, compilation_config={"custom_ops":['none', "+rms_norm", "+rotary_embedding"]}, ) # Generate texts from the prompts. outputs = llm.generate(prompts, sampling_params) for output in outputs: prompt = output.prompt generated_text = output.outputs[0].text print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}") ``` --------- Signed-off-by: Vincent Yuan <[email protected]> Signed-off-by: Yikun Jiang <[email protected]> Signed-off-by: angazenn <[email protected]> Co-authored-by: Vincent Yuan <[email protected]> Co-authored-by: angazenn <[email protected]> Co-authored-by: wangxiyuan <[email protected]> Co-authored-by: leo-pony <[email protected]> Co-authored-by: shen-shanshan <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What this PR does / why we need it?
This PR is extension of #914 and #1204 , which support PanguProMoE on 310p platform. Currently
fused_experts_310pis only implemented for PanguProMoE.Does this PR introduce any user-facing change?
How was this patch tested?