skip silu_mul_fp8_quant_deep_gemm_cuda and remove zero_overhead

1bd3ae33 · zhuwenwen · 9bf1b213 · 9bf1b213 · 9bf1b213
Commit 1bd3ae33 authored Oct 11, 2025 by zhuwenwen
Expand all Hide whitespace changes
Inline Side-by-side

Showing with 0 additions and 759 deletions

vllm/zero_overhead/v1/gpu_model_runner.py vllm/zero_overhead/v1/gpu_model_runner.py +0 -747

vllm/zero_overhead/v1/outputs.py vllm/zero_overhead/v1/outputs.py +0 -12

No files found.
--- a/vllm/zero_overhead/v1/gpu_model_runner.py
+++ b/vllm/zero_overhead/v1/gpu_model_runner.py
--- a/vllm/zero_overhead/v1/outputs.py
+++ b/vllm/zero_overhead/v1/outputs.py
-
-from dataclasses import dataclass
-from vllm.v1.outputs import ModelRunnerOutput
-
-@dataclass
-class ZeroV1ModelRunnerOutput(ModelRunnerOutput):
-    # [num_reqs]
-    fix_req_ids: list[str] = None
-    fix_sampled_token_ids:list[list[int]] = None
-    fix_draft_req_ids:list[str] = None
-    fix_draft_tokens_ids:list[list[int]] = None
-    is_output_valid:bool = True
\ No newline at end of file