fix(debug): move debug_dump out of h20_ops so other platforms can import it

The dump hooks live in five platform-neutral files -- `sampler.py`, `mlp.py`, `deepseek.py`,
`decoder_layer.py`, `model_runner.py` -- and all of them imported
`deepinfer.h20_ops.debug_dump`. That is wrong on every platform except SM90: `h20_ops/__init__.py`
calls `extend_import_patches(override=True, ...)` at module scope, so importing it from shared code
installs the SM90 import shims globally. On an SM100 machine that replaces
`flash_mla.decode_mla_mqa_sparse`, `flash_mla.prefill_attn_varlen_sparse` and
`deep_select.interface.topk` with the Hopper implementations, and on NPU it would do the same
before the Ascend shims get a chance to matter.

`debug_dump` itself has nothing platform-specific in it -- `os`, `pathlib`, `numpy`, `torch` --
so it moves to `deepinfer/debug_dump.py` and the five imports follow. Verified that importing it
no longer pulls `h20_ops` into `sys.modules`, and re-ran the end-to-end check on H20: same output
token for token, `[17607, 2793, 3139, 666, 6127, 666, 320, 1]`.

This bug is already in the open PR, so it needs to land before that PR is worth reviewing further.

H20-DEBUG-PLAN.md

@@ -366,12 +366,35 @@ prefill 选中了正确的 token，误差只把 margin 压缩了 12 倍。但端
 - `scripts/h20_kv_roundtrip.py`：KV cache 闭环 round-trip（不依赖 ref）
 - `scripts/h20_index_decode_check.py`：`_decode_p_sum_sm90` 的独立数值对照
 
-## P5 logprob 异常
+## P5 logprob 异常（已排查，未修，非阻塞）
 
 当前 8 个 token 的 `token_logprobs` 全是 `0.0`（概率=1），不正常。
 
-- [ ] P5.1 确认是采样器 bug 还是 logits 极端（打印 logits 的 max/median）
-- [ ] P5.2 检查 `DEEPINFER_SAMPLER_FORCE_TOPK=4096` 与 logprob 回填的关系
+### 已排除（约 20 分钟静态排查 + 单测）
+
+| 嫌疑 | 结论 |
+|---|---|
+| `map_lookup` kernel | 无罪。单测 6 passed，`by_key` + float32 + `force_topk=4096` 全覆盖，与 `map_lookup_ref` 逐元素相等 |
+| sampler 全部 kernel | 无罪。`sampler.py -m "not benchmark"` → **74 passed / 0 failed** |
+| `SampledInfo.from_reqcnt` 的 `torch.zeros` | 死代码，全仓库无调用点；`update(is_final, candidate)` 也无调用点 |
+| sampler→engine 字段传递 | 直通，`llm_engine.py:747` 原样传 `output.token_logprobs` |
+
+**一个反向线索**：`map_lookup` 里 `out = torch.empty`，键未命中时本应写 `-inf` 而**不是 0**。
+所以 0.0 更像「上层根本没把值带下来」，而不是「查表查空了」。
+
+### 剩余候选与判定路径
+
+- `process_sampling` 返回的 `logprobs` 本身为 0（`fused_sample` 的 logprob 输出路径；
+  现有单测只覆盖 kernel 本身，没有覆盖「整个 forward 的 logprob 输出」）
+- `build_request_outputs` 里逐 token 对象的属性回填
+
+判定只需跑 1 次整机（~5 min）：在 sampler 里打印 `logprobs.max()` 与 `token_logprobs_cur`。
+sampler 层就是 0 → 定位在 `fused_sample`；sampler 层正常 → 定位在 output 回填。
+
+### 为什么留着不修
+
+不影响推理正确性，只影响 logprob 字段的可用性（AIME 打分、perplexity 这类评估用途）。
+预估典型 1 h、最坏 2 h（若牵涉 MTP 异步 logprob 回填），与本次 SM90 支持的目标无关。
 
 ---
 

deepinfer/model_executor/layers/sampler.py

@@ -11,8 +11,8 @@ import torch
 import torch.nn as nn
 from deep_select.interface import topk
 
+from deepinfer import debug_dump as _debug_dump
 from deepinfer import envs
-from deepinfer.h20_ops import debug_dump as _debug_dump
 from deepinfer.logger import init_logger
 from deepinfer.model_executor.input_metadata import InputMetadata
 from deepinfer.model_executor.layers.mtp_info_pool import MTPInfoPool

deepinfer/model_executor/models/decoder_layer.py

@@ -5,7 +5,7 @@ import torch
 from torch import nn
 
 from deepinfer import AttrDict, envs
-from deepinfer.h20_ops import debug_dump as _debug_dump
+from deepinfer import debug_dump as _debug_dump
 from deepinfer.logger import init_logger
 from deepinfer.model_executor.input_metadata import InputMetadata
 from deepinfer.model_executor.input_metadata.yoco import YocoMetadataMixin

deepinfer/model_executor/models/deepseek.py

@@ -9,8 +9,8 @@ import torch
 from torch import nn
 
 from deepinfer import AttrDict, envs
+from deepinfer import debug_dump as _debug_dump
 from deepinfer.engine.engine_type import EngineType
-from deepinfer.h20_ops import debug_dump as _debug_dump
 from deepinfer.logger import init_logger
 from deepinfer.model_executor import eplb
 from deepinfer.model_executor.input_metadata import InputMetadata

deepinfer/model_executor/models/v4_modules/mlp.py

@@ -21,8 +21,8 @@ from tile_kernels.quant import swiglu_forward_and_per_token_cast
 from torch import nn
 
 from deepinfer import PLATFORM, AttrDict, envs
+from deepinfer import debug_dump as _debug_dump
 from deepinfer.engine.engine_type import EngineType
-from deepinfer.h20_ops import debug_dump as _debug_dump
 from deepinfer.logger import init_logger
 from deepinfer.model_executor import eplb
 from deepinfer.model_executor.input_metadata import InputMetadata

deepinfer/worker/model_runner.py

@@ -11,11 +11,11 @@ import numpy as np
 import torch
 import torch.distributed as dist
 
+from deepinfer import debug_dump as _debug_dump
 from deepinfer import envs
 from deepinfer._C.engine import prepare_sampler_inputs, update_prompt_logprobs  # pyright: ignore[reportMissingModuleSource]
 from deepinfer.config import CacheConfig, ModelConfig, ParallelConfig, SchedulerConfig
 from deepinfer.engine.engine_type import EngineType
-from deepinfer.h20_ops import debug_dump as _debug_dump
 from deepinfer.logger import init_logger
 from deepinfer.model_executor.input_metadata import InputMetadata
 from deepinfer.model_executor.layers.mtp_info_pool import get_nextn_pad_token_ids