xc-llm-ascend/vllm_ascend/patch/worker/patch_rejection_sampler.py

import vllm.v1.sample.rejection_sampler as rs

from vllm_ascend.sample.rejection_sampler import apply_sampling_constraints, expand_batch_to_tokens, rejection_sample

# TODO: delete this patch after apply_sampling_constraints and rejection_sample
#   are extracted to as class func of RejectionSampler
rs.apply_sampling_constraints = apply_sampling_constraints
rs.rejection_sample = rejection_sample
rs.expand_batch_to_tokens = expand_batch_to_tokens
[Feat] Refactor rejection sampler (#4975) ### What this PR does / why we need it? Currently, we are using `AscendRejctionSampler` that extends from `RejctionSampler` in spec decoding. `AscendRejctionSampler` override `forward` of `RejctionSampler`, only aming to replace `rejection_sample` func. This causes a lot of code of `RejctionSampler` cannot be reused, for example: - https://github.com/vllm-project/vllm/pull/19482 - https://github.com/vllm-project/vllm/pull/26060 - https://github.com/vllm-project/vllm/pull/29223 #### Proposed Change: - Delete `AscendRejctionSampler` and use `RejctionSampler` directly in model runner. - Patch `RejctionSampler.expand_batch_to_tokens` and `RejctionSampler.rejection_sample`, maybe a better way is to make them as custom ops. - Modify `NPUModelRunner` following https://github.com/vllm-project/vllm/pull/26060 ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? - [x] test logits processor for spec decoding - [x] test logprobs for spec decoding - [x] test logprobs for spec decoding + async shcheduling (test with https://github.com/vllm-project/vllm-ascend/pull/4893/) - vLLM version: v0.12.0 - vLLM main: https://github.com/vllm-project/vllm/commit/ad32e3e19ccf0526cb6744a5fed09a138a5fb2f9 --------- Signed-off-by: realliujiaxu <realliujiaxu@163.com> 2025-12-16 11:32:26 +08:00			`import vllm.v1.sample.rejection_sampler as rs`

[Lint]Style: Convert `vllm-ascend/` to ruff format(Batch #10) (#6173) ### What this PR does / why we need it? Scope of Changes: \| File Path \| \| :--- \| \|`vllm_ascend/ops/layer_shard_linear.py`\| \|`vllm_ascend/ops/linear.py`\| \|`vllm_ascend/ops/linear_op.py`\| \|`vllm_ascend/worker/worker.py`\| \| ` vllm_ascend/patch/worker/patch_bert.py` \| \| ` vllm_ascend/patch/worker/patch_deepseek.py` \| \| ` vllm_ascend/patch/worker/patch_distributed.py` \| \| ` vllm_ascend/patch/worker/patch_module.py` \| \| ` vllm_ascend/patch/worker/patch_multimodal_merge.py` \| \| ` vllm_ascend/patch/worker/patch_qwen3_next.py` \| \| ` vllm_ascend/patch/worker/patch_qwen3_next_mtp.py` \| \| ` vllm_ascend/patch/worker/patch_rejection_sampler.py` \| \| ` vllm_ascend/patch/worker/patch_rope.py` \| \| ` vllm_ascend/patch/worker/patch_triton.py` \| \| ` vllm_ascend/patch/worker/patch_unquantized_gemm.py` \| \| ` vllm_ascend/patch/worker/patch_v2_egale.py` \| \|` vllm_ascend/worker/npu_input_batch.py`\| \|` vllm_ascend/worker/v2/aclgraph_utils.py`\| \|` vllm_ascend/worker/v2/attn_utils.py`\| \|` vllm_ascend/worker/v2/model_runner.py`\| \|` vllm_ascend/worker/v2/sample/gumbel.py`\| \|` vllm_ascend/worker/v2/sample/penalties.py`\| \|` vllm_ascend/worker/v2/sample/sampler.py`\| \|` vllm_ascend/worker/v2/spec_decode/__init__.py`\| \|` vllm_ascend/worker/v2/spec_decode/eagle.py`\| \|` vllm_ascend/worker/v2/states.py`\| ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? - vLLM version: v0.14.0 - vLLM main: https://github.com/vllm-project/vllm/commit/d68209402ddab3f54a09bc1f4de9a9495a283b60 Signed-off-by: MrZ20 <2609716663@qq.com> Signed-off-by: SILONG ZENG <2609716663@qq.com> Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com> Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com> 2026-02-06 15:35:06 +08:00			`from vllm_ascend.sample.rejection_sampler import apply_sampling_constraints, expand_batch_to_tokens, rejection_sample`
[Feat] Refactor rejection sampler (#4975) ### What this PR does / why we need it? Currently, we are using `AscendRejctionSampler` that extends from `RejctionSampler` in spec decoding. `AscendRejctionSampler` override `forward` of `RejctionSampler`, only aming to replace `rejection_sample` func. This causes a lot of code of `RejctionSampler` cannot be reused, for example: - https://github.com/vllm-project/vllm/pull/19482 - https://github.com/vllm-project/vllm/pull/26060 - https://github.com/vllm-project/vllm/pull/29223 #### Proposed Change: - Delete `AscendRejctionSampler` and use `RejctionSampler` directly in model runner. - Patch `RejctionSampler.expand_batch_to_tokens` and `RejctionSampler.rejection_sample`, maybe a better way is to make them as custom ops. - Modify `NPUModelRunner` following https://github.com/vllm-project/vllm/pull/26060 ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? - [x] test logits processor for spec decoding - [x] test logprobs for spec decoding - [x] test logprobs for spec decoding + async shcheduling (test with https://github.com/vllm-project/vllm-ascend/pull/4893/) - vLLM version: v0.12.0 - vLLM main: https://github.com/vllm-project/vllm/commit/ad32e3e19ccf0526cb6744a5fed09a138a5fb2f9 --------- Signed-off-by: realliujiaxu <realliujiaxu@163.com> 2025-12-16 11:32:26 +08:00
			`# TODO: delete this patch after apply_sampling_constraints and rejection_sample`
			`# are extracted to as class func of RejectionSampler`
			`rs.apply_sampling_constraints = apply_sampling_constraints`
			`rs.rejection_sample = rejection_sample`
			`rs.expand_batch_to_tokens = expand_batch_to_tokens`