[Feature][PCP] Add DeepSeek-V4.1-Flash support (#59857)

Signed-off-by: wangyicong <wangyicong@bytedance.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
This commit is contained in:
Yicong Wang
2026-10-15 23:17:51 -07:00
committed by GitHub
co-authored by OpenAI Codex Lucas Wilkinson Claude Opus 5.5 Kevin H. Luu
parent 074c83a09a
commit fa75d3456d
15 changed files with 873 additions and 37 deletions
@@ -585,6 +585,7 @@ def _check_dummy_hash_model_forward(
model = model_ops.DeepseekV4Model.__new__(model_ops.DeepseekV4Model)
torch.nn.Module.__init__(model)
model.parallel_config = vllm_config.parallel_config
model.use_native_mega_moe = False
model.use_sequence_parallel = False
model.fuse_mhc_all_reduce = False