zxr2333 1d81a289d0 [P/D][BugFix]Fix proxy format processing errors & Layerwise connector performance optimization (#4043) ...

### What this PR does / why we need it?
1. Fix proxy format processing errors.
2. Layer-wise connector performance optimization.

### Does this PR introduce _any_ user-facing change?
No.

### How was this patch tested?
By CI.

- vLLM version: v0.11.0
- vLLM main:
83f478bb19

---------

Signed-off-by: nwpu-zxr <zhouxuerong2@huawei.com>
Co-authored-by: wangxiaoteng <wangxiaoteng@huawei.com>

2025-11-08 18:44:06 +08:00

..

chat_templates

[MM][Doc] Update online serving tutorials for Qwen2-Audio (#3606)

2025-10-27 16:58:03 +08:00

disaggregated_prefill_v1

[P/D][BugFix]Fix proxy format processing errors & Layerwise connector performance optimization (#4043)

2025-11-08 18:44:06 +08:00

eplb

[Misc][V0 Deprecation] Add __main__ guard to all offline examples (#1837)

2025-07-17 14:13:30 +08:00

external_online_dp

[Feature] Support moe multi-stream for aclgraph. (#2946)

2025-09-19 11:06:45 +08:00

offline_data_parallel.py

Upgrade to new vllm commit (#3719)

2025-10-25 15:36:32 +08:00

offline_disaggregated_prefill_npu.py

Fix VLLM_ASCEND_LLMDD_RPC_PORT renaming (#3108)

2025-09-23 10:33:04 +08:00

offline_embed.py

[Misc][V0 Deprecation] Add __main__ guard to all offline examples (#1837)

2025-07-17 14:13:30 +08:00

offline_external_launcher.py

Upgrade to new vllm commit (#3719)

2025-10-25 15:36:32 +08:00

offline_inference_audio_language.py

Fix some ci issue and refactor modelrunner (#2445)

2025-08-20 09:01:04 +08:00

offline_inference_npu_long_seq.py

support cp&dcp (#3260)

2025-10-24 10:32:01 +08:00

offline_inference_npu_tp2.py

[Misc][V0 Deprecation] Add __main__ guard to all offline examples (#1837)

2025-07-17 14:13:30 +08:00

offline_inference_npu.py

[Misc][V0 Deprecation] Add __main__ guard to all offline examples (#1837)

2025-07-17 14:13:30 +08:00

offline_inference_sleep_mode_npu.py

Upgrade to new vllm commit (#3719)

2025-10-25 15:36:32 +08:00

offline_weight_load.py

Upgrade to new vllm commit (#3719)

2025-10-25 15:36:32 +08:00

prompt_embed_inference.py

[feature] Prompt Embeddings Support for v1 Engine (#3026)

2025-10-30 17:15:57 +08:00

prompt_embedding_inference.py

[Misc][V0 Deprecation] Add __main__ guard to all offline examples (#1837)

2025-07-17 14:13:30 +08:00

run_dp_server.sh

[Feature] Support moe multi-stream for aclgraph. (#2946)

2025-09-19 11:06:45 +08:00