[SpecDecode] Add spec decode support (#500)

### What this PR does / why we need it?
Backport: https://github.com/vllm-project/vllm-ascend/pull/252
This support speculative decoding in Ascend, including speculating with
a draft model、by matching n-grams in the prompt、using MLP speculators
and using EAGLE based draft models.

Backport: https://github.com/vllm-project/vllm-ascend/pull/423
spec decode MultiStepWorker support TP1DraftModelRunner fully, support
run the draft_model_runner with multi-step prepare on the NPU directly
and support draft_model_runner use MLA.

1. before this pr, `MultiStepWorker` would not step into the branch
using NPU prepare, but only into the branch using CPU prepare (`line 52`
of `vllm_ascend/patch/patch_multi_step_worker.py`). Although this has
`no effect` on the `correct operation` of speculative decoding and the
performance of the two branches is basically the same as of the current
version, I support entering this branch in this PR. In general, there
are two main changes in `patch_multi_step_worker.py`: first, the
`is_cuda_like()` check is removed and the `TP1DraftModelRunner`
rewritten in vllm_ascend is used; second, the
`supports_gpu_multi_step()` function is made to return true on NPU
devices when outer Multi_step_worker could work correct.

3. before this pr, `TP1DraftModelRunner` only supports Attention on NPU,
but not MLA. The relevant adaptation is in
`vllm_ascend/worker/draft_model_runner.py`. Although I don’t know why
the `input_positions` of `model_input.attn_metadata` in vllm-ascend
needs to be added in `execute_model`, it is done in `model_runner.py`,
so I also made corresponding changes. Otherwise, when atten_backend is
MLA, it will prompt that input_positions cannot be found.

4. I commented out two lines in `draft_model_runner.py` in `line118` to
support the scenario of K>1.
  ```
  # lora_mapping=model_input.lora_mapping,
  # lora_requests=model_input.lora_requests,
  ```
I added comments. In the future, when vllm-ascend supports lora feature,
the changes here can be restored.

TODO：
- [ ] revert the patch when the related issues are addressed in vllm

### How was this patch tested?
CI passed with new added test.
- e2e test for medusa proposer:
tests/singlecard/spec_decode/e2e/test_medusa_correctness.py
- e2e test for mlp proposer:
tests/singlecard/spec_decode/e2e/test_mlp_correctness.py
- e2e test for n-gram proposer:
tests/singlecard/spec_decode/e2e/test_ngram_correctness.py

Tests for patched files:
- tests/singlecard/spec_decode/test_dynamic_spec_decode.py
- tests/singlecard/spec_decode/test_multi_step_worker.py
- tests/singlecard/spec_decode/test_ngram_worker.py
- tests/singlecard/spec_decode/test_spec_decode_worker.py

---------

Signed-off-by: MengqingCao <cmq0113@163.com>
Co-authored-by: mengwei805 <mengwei25@huawei.com>

.github/workflows/vllm_ascend_test.yaml

@@ -122,10 +122,10 @@ jobs:
           VLLM_USE_V1: 0
         run: |
           if [[ "${{ matrix.os }}" == "linux-arm64-npu-1" ]]; then
-            pytest -sv tests/singlecard
+            pytest -sv tests/singlecard/test_offline_inference.py
             pytest -sv tests/ops
           else
-            pytest -sv tests/multicard
+            pytest -sv tests/multicard/test_offline_inference_distributed.py
             pytest -sv tests/ops
           fi
 
@@ -135,13 +135,35 @@ jobs:
           VLLM_WORKER_MULTIPROC_METHOD: spawn
         run: |
           if [[ "${{ matrix.os }}" == "linux-arm64-npu-1" ]]; then
-            pytest -sv tests/singlecard
+            pytest -sv tests/singlecard/test_offline_inference.py
             pytest -sv tests/ops
           else
-            pytest -sv tests/multicard
+            pytest -sv tests/multicard/test_offline_inference_distributed.py
             pytest -sv tests/ops
           fi
 
+      - name: Check for changes in Speculative Decode
+        id: filter_spec_decode
+        uses: dorny/paths-filter@v2
+        with:
+          filters: |
+            speculative_tests_changed:
+              - "tests/singlecard/spec_decode/**"
+              - "tests/multicard/spec_decode_e2e/**"
+              - "vllm_ascend/worker/multi_step_runner.py"
+              - "vllm_ascend/worker/multi_step_worker.py"
+              - "vllm_ascend/patch/patch_rejection_sampler.py"
+              - "vllm_ascend/patch/patch_spec_decode_worker.py"
+              - "vllm_ascend/patch/patch_multi_step_worker.py"
+      - name: Run vllm-project/vllm-ascend Speculative Decode test
+        env:
+          HF_ENDPOINT: https://hf-mirror.com
+        if: steps.filter_spec_decode.outputs.speculative_tests_changed
+        run: |
+          if [[ "${{ matrix.os }}" == "linux-arm64-npu-1" ]]; then
+            pytest -sv tests/singlecard/spec_decode
+          fi
+
       - name: Run vllm-project/vllm test for V0 Engine
         env:
           VLLM_USE_V1: 0