[Rebase] Rebase to vllm v0.21.0 (#3530)

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: Zhou Taichang <tzhouam@connect.ust.hk>
Signed-off-by: NumberWan <wantszkin2003@gmail.com>
Signed-off-by: Divyansh Singhvi <divyanshsinghvi@gmail.com>
Signed-off-by: dsinghvi <divyanshsinghvi@gmail.com>
Signed-off-by: Dnoob <dxpouo@gmail.com>
Signed-off-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
Signed-off-by: knlnguyen1802 <knlnguyen1802@gmail.com>
Signed-off-by: rein yang <ruiruyang2@gmail.com>
Signed-off-by: Nick Cao <ncao@redhat.com>
Signed-off-by: zhumingjue <zhumingjue@huawei.com>
Signed-off-by: Ricardo Noriega De Soto <rnoriega@redhat.com>
Signed-off-by: lyj-jjj <liuyingjun5@huawei.com>
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Signed-off-by: wangyu <410167048@qq.com>
Signed-off-by: weizhoublue <weizhoublue@github.com>
Signed-off-by: weizhou.lan@daocloud.io <weizhou.lan@daocloud.io>
Signed-off-by: dengyunyang <584797741@qq.com>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Signed-off-by: David Chen <530634352@qq.com>
Signed-off-by: Jie Liu <33612777+keeper-jie@users.noreply.github.com>
Signed-off-by: Yueqian Lin <linyueqian@outlook.com>
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Signed-off-by: natureofnature <wzliu@connect.hku.hk>
Signed-off-by: bjf-frz <frz123db@gmail.com>
Signed-off-by: amy-why-3459 <wuhaiyan17@huawei.com>
Signed-off-by: KexiongYu <yukexiong1@huawei.com>
Signed-off-by: Huang, Zeyu <11222265+fhfuih@users.noreply.github.com>
Signed-off-by: Zeyu Huang | 黃澤宇 <11222265+fhfuih@users.noreply.github.com>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: NumberWan <wantszkin2003@gmail.com>
Co-authored-by: dsinghvi <divyanshsinghvi@gmail.com>
Co-authored-by: Dnoob <dxpouo@gmail.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>
Co-authored-by: knlnguyen1802 <knlnguyen1802@gmail.com>
Co-authored-by: Samit <285365963@qq.com>
Co-authored-by: rein yang <73573651+R2-Y@users.noreply.github.com>
Co-authored-by: Nick Cao <ncao@redhat.com>
Co-authored-by: zhumingjue138 <zhumingjue@huawei.com>
Co-authored-by: Ricardo Noriega <rnoriega@redhat.com>
Co-authored-by: lyj-jjj <liuyingjun5@huawei.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: gcanlin <canlinguosdu@gmail.com>
Co-authored-by: wangyu <53896905+yenuo26@users.noreply.github.com>
Co-authored-by: weizhoublue <45163302+weizhoublue@users.noreply.github.com>
Co-authored-by: weizhoublue <weizhoublue@github.com>
Co-authored-by: dengyunyang <584797741@qq.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: WeiQing Chen <40507679+david6666666@users.noreply.github.com>
Co-authored-by: Jie Liu <33612777+keeper-jie@users.noreply.github.com>
Co-authored-by: Yueqian Lin <linyueqian@outlook.com>
Co-authored-by: NATURE <wzliu@connect.hku.hk>
Co-authored-by: bjf-frz <frz123db@gmail.com>
Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
Co-authored-by: Y. Fisher <yukexiong1@huawei.com>
Co-authored-by: Zeyu Huang | 黃澤宇 <11222265+fhfuih@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

vllm_omni/model_executor/models/common/qwen3_code_predictor.py

@@ -351,8 +351,10 @@ class CodePredictorBaseModel(nn.Module):
         # native bf16 support (Turing, Volta).  The RMSNorm and RoPE
         # layers already upcast internally; this extends the same
         # treatment to attention and MLP.
+        # autocast to float32 is unsupported on CPU; skip fp32 upcast there
+        # (CPU uses full-precision intermediates internally).
         input_dtype = inputs_embeds.dtype
-        use_fp32 = input_dtype == torch.float16
+        use_fp32 = input_dtype == torch.float16 and inputs_embeds.device.type != "cpu"
         if use_fp32:
             inputs_embeds = inputs_embeds.float()
         hidden_states = inputs_embeds

vllm_omni/model_executor/models/common/snake_activation.py

@@ -61,8 +61,9 @@ class SnakeBeta(nn.Module):
             x = tl.load(x_ptr + bid * stride_b + cid * stride_c + t_off, mask=mask, other=0.0)
             ea = tl.load(exp_alpha_ptr + cid)
             ib = tl.load(inv_beta_ptr + cid)
-            sin_val = tl.sin(x * ea)
-            result = x + ib * sin_val * sin_val
+            x_float = x.to(tl.float32)
+            sin_val = tl.sin(x_float * ea)
+            result = x + (ib * sin_val * sin_val).to(x.dtype)
 
             tl.store(out_ptr + bid * stride_b + cid * stride_c + t_off, result, mask=mask)
 

vllm_omni/model_executor/models/hunyuan_image3/hunyuan_image3.py

@@ -27,17 +27,8 @@ from vllm.distributed import (
 )
 from vllm.inputs import MultiModalDataDict
 from vllm.logger import init_logger
+from vllm.model_executor.layers.fused_moe import FusedMoE as SharedFusedMoE
 from vllm.model_executor.layers.fused_moe import fused_moe_make_expert_params_mapping
-
-try:
-    from vllm.model_executor.layers.fused_moe.shared_fused_moe import SharedFusedMoE
-except ImportError:
-    # PyPI vllm 0.20.x neither exports `SharedFusedMoE` from the package top-level
-    # nor ships a `shared_fused_moe.py` submodule. The functionality lives on
-    # `FusedMoE` directly (which gained a `shared_experts` parameter), so alias
-    # the symbol — call sites only use the classmethod `make_expert_params_mapping`
-    # and `__init__(shared_experts=..., ...)` which are present on `FusedMoE`.
-    from vllm.model_executor.layers.fused_moe import FusedMoE as SharedFusedMoE
 from vllm.model_executor.layers.linear import (
     ColumnParallelLinear,
     ReplicatedLinear,

vllm_omni/model_executor/models/moss_tts_nano/modeling_moss_tts_nano.py

@@ -160,7 +160,7 @@ class MossTTSNanoForGeneration(nn.Module):
     def load_weights(self, weights: Iterable[tuple[str, torch.Tensor]]) -> set[str]:
         with self._lock:
             if self._lm is not None:
-                return set()
+                return None
             _patch_torchaudio_load()
 
             try:
@@ -233,7 +233,7 @@ class MossTTSNanoForGeneration(nn.Module):
         # iterator so the underlying stream is closed cleanly.
         for _ in weights:
             pass
-        return set()
+        return None
 
     # ------------------------------------------------------------------
     # Dummy run support

vllm_omni/model_executor/models/qwen3_tts/tokenizer_12hz/modeling_qwen3_tts_tokenizer_v2.py

@@ -534,6 +534,10 @@ class Qwen3TTSTokenizerV2DecoderTransformerModel(Qwen3TTSTokenizerV2DecoderPreTr
         cache_position=None,
         **kwargs,
     ) -> BaseModelOutputWithPast:
+        r"""
+        cache_position (`torch.LongTensor` of shape `(sequence_length)`, *optional*):
+            Indices depicting the position of the input sequence tokens in the sequence. Used to update the cache.
+        """
         if input_ids is not None:
             raise ValueError("input_ids is not expected")
         if (input_ids is None) ^ (inputs_embeds is not None):