Icey
e7618d9414
[2/N][Refactor][Qwen3-Next] remove redundant methods and patch methods in Qwen3NextGatedDeltaNet ( #3082 )
...
### What this PR does / why we need it?
remove redundant methods and patch methods in Qwen3NextGatedDeltaNet
involved causal_conv1d_fn, causal_conv1d_update_npu, fused_gdn_gating,
fused_reccrrent_gated_delta_rule, torch_chunk_gated_delta_rule,
RMSNormGated
### Does this PR introduce _any_ user-facing change?
N/A
### How was this patch tested?
```
def main():
prompts = [
"The future of AI is",
]
# Create a sampling params object.
sampling_params = SamplingParams(max_tokens=100, temperature=0.6, top_k=40, top_p=0.95)
# Create an LLM.
llm = LLM(
model="Qwen/Qwen3-Next-80B-A3B-Instruct",
tensor_parallel_size=4,
enforce_eager=True,
trust_remote_code=True,
max_model_len=256,
gpu_memory_utilization=0.7,
block_size=64,
)
# 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}")
```
CI passed with new added/existing test.
- vLLM version: v0.10.2
- vLLM main:
5aeb9254521790571317@qq.com >
2025-09-24 11:25:42 +08:00
Icey
14b39d3c70
[1/N][Refactor][Qwen3-Next] remove redundant Qwen3NextSparseMoeBlock and Qwen3NextAttention ( #3019 )
...
### What this PR does / why we need it?
remove redundant Qwen3NextSparseMoeBlock and Qwen3NextAttention
### Does this PR introduce _any_ user-facing change?
N/A
### How was this patch tested?
```
def main():
prompts = [
"The future of AI is",
]
sampling_params = SamplingParams(max_tokens=100, temperature=0.6, top_k=40, top_p=0.95)
# Create an LLM.
llm = LLM(
# model="/root/.cache/modelscope/hub/models/Qwen/Qwen3-30B-A3B",
model="Qwen/Qwen3-Next-80B-A3B-Instruct",
tensor_parallel_size=4,
enforce_eager=True,
trust_remote_code=True,
max_model_len=256,
gpu_memory_utilization=0.7,
block_size=64,
)
# 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}")
```
- vLLM version: v0.10.2
- vLLM main:
9d1c50a5ac1790571317@qq.com >
2025-09-22 11:24:08 +08:00
22dimensions
0942d9aaab
[3/N][Refactor][Quantization]remove packed_modules_mapping from models ( #3021 )
...
### What this PR does / why we need it?
Some custom models in vllm-ascend define packed_modules_mapping, which
prevent keeping same model class with vllm community. So move these
custom packed_modules_mapping to quant utils.py. After this pr, some
custom models can be removed.
### Does this PR introduce _any_ user-facing change?
tested by CI
### How was this patch tested?
tested by CI
- vLLM version: v0.10.2
- vLLM main:
5089fd749cwaitingwind@foxmail.com >
2025-09-19 20:50:14 +08:00
