[Docs] Fix two docs build warnings (#51014)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Harry Mellor committed
Aug 4, 2026 at 13:29 UTC
1eb3694521a67446ae23ce1e6dd04093e944a08e
2 files changed
+2
-2
docs/design/moe_kernel_features.md
+1
-1
@@ -32,7 +32,7 @@ th {
32
33
| Backend | Output act. format | Quant. types | Quant. format | Async | Apply Weight On Input | Subclass |
34
| ------- | ------------------ | ------------ | ------------- | ----- | --------------------- | --------- |
35
-| naive | standard | all<sup>1</sup> | G,A,T | N | <sup>6</sup> | [layer.py][vllm.model_executor.layers.fused_moe.runner.MoERunner] |
35
+| naive | standard | all<sup>1</sup> | G,A,T | N | <sup>6</sup> | [`MoERunner`][vllm.model_executor.layers.fused_moe.runner.moe_runner.MoERunner] |
36
| deepep_high_throughput | standard | fp8 | G(128),A,T<sup>2</sup> | Y | Y | [`DeepEPHTPrepareAndFinalize`][vllm.model_executor.layers.fused_moe.prepare_finalize.deepep_ht.DeepEPHTPrepareAndFinalize] |
37
| deepep_low_latency | batched | fp8 | G(128),A,T<sup>3</sup> | Y | Y | [`DeepEPLLPrepareAndFinalize`][vllm.model_executor.layers.fused_moe.prepare_finalize.deepep_ll.DeepEPLLPrepareAndFinalize] |
38
| flashinfer_nvlink_two_sided | standard | nvfp4,fp8 | G,A,T | N | N | [`FlashInferNVLinkTwoSidedPrepareAndFinalize`][vllm.model_executor.layers.fused_moe.prepare_finalize.flashinfer_nvlink_two_sided.FlashInferNVLinkTwoSidedPrepareAndFinalize] |
vllm/model_executor/kernels/linear/mxfp6/base.py
+1
-1
@@ -18,7 +18,7 @@ class MxFp6LinearLayerConfig:
18
19
Attributes:
20
weight_quant_key: Identifies the weight quantization format. Can be
21
- kMxfp6E2M3Static or kMxfp6E3M2Static.
21
+ kMxfp6E2M3Static or kMxfp6E3M2Static.
22
activation_quant_key: Identifies the activation quantization format,
23
or `None` when activations must not be quantized.
24
"""