Shaoxu Cheng 83bd77c983 [310p]: add rmsnorm gated fallback and unit test (#7424) ...

### What this PR does / why we need it?
RFC #7394
310P cannot use the fused `rmsnormgated` operator and must fall back to
the native implementation.

### Does this PR introduce _any_ user-facing change?
NO
### How was this patch tested?
ut
- vLLM version: v0.17.0
- vLLM main:
4497431df6

---------

Signed-off-by: Tflowers-0129 <2906339855@qq.com>

2026-03-24 09:00:11 +08:00

..

_310p

[310p]: add rmsnorm gated fallback and unit test (#7424)

2026-03-24 09:00:11 +08:00

attention

[Feature]Supports DSv3.1 PD separation and C8 quantization (#7222)

2026-03-16 22:49:05 +08:00

batch_invariant

[Feature] Add docs of batch invariance and make some extra operators patch (#6910)

2026-03-05 09:12:40 +08:00

compilation

[Bugfix] Fix slow hasattr in ACLGraphWrapper.__getattr__ (#7442)

2026-03-23 09:26:24 +08:00

core

[MM][Bugfix] Update hf_config to hf_text_config (#5319)

2026-01-06 16:41:39 +08:00

device_allocator

[CPU binding] Implement global CPU slicing and improve IRQ binding for Ascend NPUs (#6945)

2026-03-03 17:20:52 +08:00

distributed

Main2main upgrade vllm commit to 03 19 17:00 (#7478)

2026-03-23 16:25:57 +08:00

eplb

[EPLB] Reduce the memory used for batch_isend_irecv (#7344)

2026-03-20 12:25:58 +08:00

fake_weight

[CI] Add unit test framework (#1201)

2025-06-16 18:32:28 +08:00

kv_connector

[P/D][PCP] mooncake layerwise support pcp function (#6627)

2026-02-12 11:02:25 +08:00

model_loader/netloader

Revert "moe_gating_top_k" (#5512)

2025-12-30 15:05:47 +08:00

ops

[refactor] replace scattered business kwargs with typed request objects and explicit stage boundaries (#7024)

2026-03-20 23:23:57 +08:00

patch/worker/patch_common

[Feature] Optimize Qwen3.5/Qwen3Next GDN prefill by prebuilding chunk metadata (#7487)

2026-03-22 23:09:23 +08:00

quantization

[refactor] replace scattered business kwargs with typed request objects and explicit stage boundaries (#7024)

2026-03-20 23:23:57 +08:00

sample

[Refactor] Import global var form vllm instead of overwirte it (#5469)

2026-01-07 18:41:45 +08:00

spec_decode

[Bugfix] Fix padding logic in eagle proposer for kimi25 (#7348)

2026-03-21 16:57:22 +08:00

worker

[Bugfix] Fix multi-instance serving OOM on single card (#7427)

2026-03-23 14:22:59 +08:00

__init__.py

[2/4][Refactor] Refactor torchair utils (#1892)

2025-07-21 19:43:30 +08:00

base.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

conftest.py

[Main2Main] Upgrade vllm commit to 0105 (#5595)

2026-01-06 08:44:29 +08:00

test_ascend_config.py

[Triton][Config] Add muls_add triton kernel and refactor AscendCompilationConfig (#5518)

2026-03-02 17:54:25 +08:00

test_envs.py

[Misc] Remove redundant imported envs, using envs_ascend instead (#2193)

2025-08-14 09:33:39 +08:00

test_platform.py

[Platform][BugFix] Preserve hybrid block size on Ascend (#7528)

2026-03-22 11:21:49 +08:00

test_utils.py

[300I][Bugfix] fix unquant model weight nd2nz error (#6851)

2026-03-03 15:57:26 +08:00