[Bugfix][Spec Decode] Fix wrong valid_mask for padded speculation when chunked...

[Bugfix][Spec Decode] Fix wrong valid_mask for padded speculation when chunked prefill occurs (#26231)
Signed-off-by: seven-mile <i@7li.moe>
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Co-authored-by: Benjamin Chislett <bchislett@nvidia.com>

vllm/v1/spec_decode/eagle.py

@@ -522,10 +522,6 @@ class EagleProposer:
         )
 
         # Generate a mask for all valid tokens within those requests
-        max_gen_len = sampled_token_ids.shape[-1]
-        if max_gen_len == 1:
-            valid_mask = torch.ones_like(valid_sampled_token_ids_gpu, dtype=torch.bool)
-        else:
         valid_mask = (valid_sampled_token_ids_gpu != -1) & (
             valid_sampled_token_ids_gpu < gpu_input_batch.vocab_size
         )