bc69d7cfe1
Bump vLLM version to v0.11.2 What's broken and changed by vLLM: 1. structured_output is broken by https://github.com/vllm-project/vllm/pull/26866 2. get_mrope_input_positions is broken by https://github.com/vllm-project/vllm/pull/28399 3. graph mode is broken by https://github.com/vllm-project/vllm/pull/25110 we'll upgrade torch to 2.8 to fix the problem later 4. embedding is broken by https://github.com/vllm-project/vllm/pull/27583 5. `get_attn_backend_cls` and attention backend is broken are broken by https://github.com/vllm-project/vllm/pull/28534 6. spec decode is broken by https://github.com/vllm-project/vllm/pull/28771 7. sp feature is broken by https://github.com/vllm-project/vllm/pull/27126 8. mtp is broken by https://github.com/vllm-project/vllm/pull/27922 9. lora is broken by https://github.com/vllm-project/vllm/pull/21068 10. execute_model is broken by https://github.com/vllm-project/vllm/pull/26866 11. `VLLM_DISABLE_SHARED_EXPERTS_STREAM` env is broken by https://github.com/vllm-project/vllm/pull/28159 12. kv cahe is broken by https://github.com/vllm-project/vllm/pull/27753 13. dp is broken by https://github.com/vllm-project/vllm/pull/25110 What's broken and changed by ourself: 1. qwen vl is broken by https://github.com/vllm-project/vllm/pull/28455 We'll remove model files in the future to avoid this kind of error 2. Engine core is broken by https://github.com/vllm-project/vllm/pull/23691 We'll remove the patch file in the future. 3. Ascend scheduler is broken by https://github.com/vllm-project/vllm/pull/28733 We'll remove ascend scheudler later. 4. qwen3-next is broken by https://github.com/vllm-project/vllm/pull/28083 We'll remove model files in the future to avoid this kind of error 5. qwen vl is broken by https://github.com/vllm-project/vllm/pull/27764. We'll remove model files in the future Known issue: 1. ray doesn't work 2. the accuracy of qwen3-next is not correct 3. qwen3-vl is broken 4. prefix cache+ ascend scheduler + deepseek v2 lite is broken. Co-authored-by: MengqingCao <cmq0113@163.com> Co-authored-by: hfadzxy <starmoon_zhang@163.com> Co-authored-by: leo-pony <nengjunma@outlook.com> Co-authored-by: 22dimensions <waitingwind@foxmail.com> Co-authored-by: shen-shanshan <467638484@qq.com> - vLLM version: v0.11.2 --------- Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com> Signed-off-by: MengqingCao <cmq0113@163.com> Signed-off-by: hfadzxy <starmoon_zhang@163.com> Signed-off-by: leo-pony <nengjunma@outlook.com> Co-authored-by: MengqingCao <cmq0113@163.com> Co-authored-by: hfadzxy <starmoon_zhang@163.com> Co-authored-by: leo-pony <nengjunma@outlook.com>
73 lines
2.5 KiB
Python
73 lines
2.5 KiB
Python
import numpy as np
|
|
import torch
|
|
from vllm.config import CUDAGraphMode
|
|
from vllm.v1.spec_decode.ngram_proposer import \
|
|
NgramProposer as VllmNgramProposer
|
|
|
|
from vllm_ascend.spec_decode.interface import Proposer, SpecDcodeType
|
|
|
|
|
|
class NgramProposer(VllmNgramProposer, Proposer):
|
|
|
|
def __init__(self, vllm_config, device, runner):
|
|
super().__init__(vllm_config)
|
|
self.name = SpecDcodeType.NGRAM
|
|
self.device = device
|
|
self.runner = runner
|
|
|
|
def load_model(self, *args, **kwargs):
|
|
# No model to load.
|
|
pass
|
|
|
|
@torch.inference_mode()
|
|
def dummy_run(self,
|
|
num_tokens,
|
|
with_prefill=None,
|
|
skip_attn=None,
|
|
num_reqs=None,
|
|
num_tokens_across_dp=None,
|
|
aclgraph_runtime_mode: CUDAGraphMode = CUDAGraphMode.NONE,
|
|
batch_descriptor=None):
|
|
pass
|
|
|
|
def generate_token_ids(self,
|
|
valid_sampled_token_ids: list[np.ndarray],
|
|
sampling_metadata=None,
|
|
scheduler_output=None,
|
|
spec_decode_metadata=None,
|
|
positions=None,
|
|
num_scheduled_tokens=None,
|
|
hidden_states=None,
|
|
attn_metadata=None,
|
|
aux_hidden_states=None) -> list[list[int]]:
|
|
valid_ngram_requests = []
|
|
for i, sampled_ids in enumerate(valid_sampled_token_ids):
|
|
num_sampled_ids = sampled_ids.shape[0]
|
|
if not num_sampled_ids:
|
|
continue
|
|
|
|
req_id = self.runner.input_batch.req_ids[i]
|
|
if req_id in self.runner.input_batch.spec_decode_unsupported_reqs:
|
|
continue
|
|
|
|
num_tokens = self.runner.input_batch.num_tokens_no_spec[i]
|
|
if num_tokens >= self.runner.input_batch.max_model_len:
|
|
# Skip requests that have already reached the max model length.
|
|
continue
|
|
|
|
start_idx = self.runner.input_batch.num_tokens_no_spec[i]
|
|
end_idx = start_idx + num_sampled_ids
|
|
self.runner.input_batch.token_ids_cpu[
|
|
i, start_idx:end_idx] = sampled_ids
|
|
|
|
valid_ngram_requests.append(i)
|
|
|
|
draft_token_ids = self.batch_propose(
|
|
len(valid_sampled_token_ids),
|
|
valid_ngram_requests,
|
|
self.runner.input_batch.num_tokens_no_spec,
|
|
self.runner.input_batch.token_ids_cpu,
|
|
)
|
|
|
|
return draft_token_ids
|