whx b6a7f07c70 [Perf][MoE] Improve MoE multistream parallel performace. (#1891) ...

This PR designs the shared expert multi-stream parallelism of
w8a8-dynamic-quantized MoE stage in more detail to achieve better
performance.

- vLLM version: v0.10.0
- vLLM main:
2cc571199b

Signed-off-by: whx-sjtu <2952154980@qq.com>

2025-07-29 23:53:19 +08:00

..

attention

[Perf] Avoid performing index selection of sin/cos cache every layer (#1890)

2025-07-29 18:06:45 +08:00

compilation

[CI] Upgrade vllm to 0.9.1 (#1165)

2025-06-11 16:33:11 +08:00

core

Disaggregate prefill for kv cache register style (#950)

2025-07-26 17:15:47 +08:00

device_allocator

[Misc]Clean up useless import from vllm (#2049)

2025-07-28 16:01:59 +08:00

distributed

[Misc]Remove PD v0 code (#2047)

2025-07-28 19:09:22 +08:00

lora

Add Custom Kernels For LoRA Performance (#1884)

2025-07-29 19:27:50 +08:00

models

[Perf][MoE] Improve MoE multistream parallel performace. (#1891)

2025-07-29 23:53:19 +08:00

multistream

[Misc] Fix logger bug (#2024)

2025-07-28 15:59:09 +08:00

ops

[Perf][MoE] Improve MoE multistream parallel performace. (#1891)

2025-07-29 23:53:19 +08:00

patch

[Feature]: implement the fusion of allreduce and matmul in prefill phase when tp is enabled (#1926)

2025-07-28 15:13:37 +08:00

quantization

[Perf][MoE] Improve MoE multistream parallel performace. (#1891)

2025-07-29 23:53:19 +08:00

sample

[Misc] Fix logger bug (#2024)

2025-07-28 15:59:09 +08:00

torchair

[main][refactor] Refactoring forward_context and model_runner_v1 (#1979)

2025-07-28 14:06:20 +08:00

worker

[Perf] Avoid performing index selection of sin/cos cache every layer (#1890)

2025-07-29 18:06:45 +08:00

__init__.py

[CI] Patch torch.library.infer_schema for fused moe ops to fix CI (#854)

2025-05-14 19:49:09 +08:00

ascend_config.py

[Dist][EP] Remove ETP/EP maintained in vllm-ascend (#1681)

2025-07-21 09:08:04 +08:00

ascend_forward_context.py

[main][refactor] Refactoring forward_context and model_runner_v1 (#1979)

2025-07-28 14:06:20 +08:00

envs.py

[Feature]: implement the fusion of allreduce and matmul in prefill phase when tp is enabled (#1926)

2025-07-28 15:13:37 +08:00

platform.py

[1/4][Refactor] Refactor torchair worker (#1885)

2025-07-21 11:50:46 +08:00

soc_info.py

Disaggregate prefill for kv cache register style (#950)

2025-07-26 17:15:47 +08:00

utils.py

[main][refactor] Refactoring forward_context and model_runner_v1 (#1979)

2025-07-28 14:06:20 +08:00