chore: import upstream snapshot with attribution

2026-07-13 13:18:33 +08:00
commit 4ececc111a
2017 changed files with 331736 additions and 0 deletions
@@ -0,0 +1,6 @@
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+from .policy import PhiPolicy
@@ -0,0 +1,91 @@
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# Create a container object to save model-specific tensors using the policy file above.
+
+from ..common_parameters import *
+from ..layer_container_base import LayerContainer
+'''
+ # HF Phi-2 model looks like this:
+
+PhiForCausalLM(
+  (model): PhiModel(
+    (embed_tokens): Embedding(51200, 2560)
+    (embed_dropout): Dropout(p=0.0, inplace=False)
+    (layers): ModuleList(
+      (0-31): 32 x PhiDecoderLayer(
+        (self_attn): PhiAttention(
+          (q_proj): Linear(in_features=2560, out_features=2560, bias=True)
+          (k_proj): Linear(in_features=2560, out_features=2560, bias=True)
+          (v_proj): Linear(in_features=2560, out_features=2560, bias=True)
+          (dense): Linear(in_features=2560, out_features=2560, bias=True)
+          (rotary_emb): PhiRotaryEmbedding()
+        )
+        (mlp): PhiMLP(
+          (activation_fn): NewGELUActivation()
+          (fc1): Linear(in_features=2560, out_features=10240, bias=True)
+          (fc2): Linear(in_features=10240, out_features=2560, bias=True)
+        )
+        (input_layernorm): LayerNorm((2560,), eps=1e-05, elementwise_affine=True)
+        (resid_dropout): Dropout(p=0.1, inplace=False)
+      )
+    )
+    (final_layernorm): LayerNorm((2560,), eps=1e-05, elementwise_affine=True)
+  )
+  (lm_head): Linear(in_features=2560, out_features=51200, bias=True)
+)
+'''
+
+
+class PhiTransformerContainer(LayerContainer):
+    """
+        Transformer layer container for the Phi model.
+    """
+    qkv_w: UnfusedQKVParameter
+    qkv_b: UnfusedQKVParameter
+    attn_out_w: AttentionOutputParameter
+    attn_out_b: AttentionOutputParameter
+    mlp_1_w: MLP1Parameter
+    mlp_1_b: MLP1Parameter
+    mlp_2_w: MLP2Parameter
+    mlp_2_b: MLP2Parameter
+    ln_gamma: NormParameter
+    ln_beta: NormParameter
+
+    PARAM_MAPPING = {
+        "self_attn.q_proj.weight": "qkv_w.q_params",
+        "self_attn.k_proj.weight": "qkv_w.k_params",
+        "self_attn.v_proj.weight": "qkv_w.v_params",
+        "self_attn.q_proj.bias": "qkv_b.q_params",
+        "self_attn.k_proj.bias": "qkv_b.k_params",
+        "self_attn.v_proj.bias": "qkv_b.v_params",
+        "self_attn.dense.weight": "attn_out_w.params",
+        "self_attn.dense.bias": "attn_out_b.params",
+        "mlp.fc1.weight": "mlp_1_w.params",
+        "mlp.fc1.bias": "mlp_1_b.params",
+        "mlp.fc2.weight": "mlp_2_w.params",
+        "mlp.fc2.bias": "mlp_2_b.params",
+        "input_layernorm.weight": "ln_gamma.params",
+        "input_layernorm.bias": "ln_beta.params",
+    }
+
+
+class PhiNonTransformerContainer(LayerContainer):
+    """
+        Non-Transformer layer container for the Phi model.
+    """
+    word_emb: EmbeddingParameter
+    word_unembed_w: UnembedParameter
+    word_unembed_b: UnembedParameter
+    final_norm_gamma: NormParameter
+    final_norm_beta: NormParameter
+
+    PARAM_MAPPING = {
+        "model.embed_tokens.weight": "word_emb.params",
+        "model.final_layernorm.weight": "final_norm_gamma.params",
+        "model.final_layernorm.bias": "final_norm_beta.params",
+        "lm_head.weight": "word_unembed_w.params",
+        "lm_head.bias": "word_unembed_b.params",
+    }
@@ -0,0 +1,199 @@
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+from typing import Iterable, Optional, Tuple
+
+import torch
+
+import deepspeed.comm as dist
+
+from ...allocator import empty_from
+from ...inference_utils import ActivationType, DtypeEnum
+from .. import *
+from ...modules.configs import *
+from ...modules.interfaces import *
+from ...ragged import RaggedBatchWrapper
+
+from .containers import PhiNonTransformerContainer, PhiTransformerContainer
+
+
+class PhiInferenceModel(DSTransformerModelBase):
+    """
+    Inference model implementation for ragged batching for Llama-2 models.
+    """
+
+    _non_transformer: Optional[PhiNonTransformerContainer]
+    """
+    Embed + unembed container. Specializing the type annotation.
+    """
+
+    _transformer: Optional[Iterable[PhiTransformerContainer]]
+    """
+    Per-layer transformer container. Specializing the type annotation.
+    """
+    """
+    Properties inherited from `DSInferenceModelBase`
+    """
+
+    @property
+    def max_sequence_length(self) -> int:
+        return self._config.max_seq_length
+
+    """
+    Properties inherited from `DSTransformerModelBase`
+    """
+
+    @property
+    def num_layers(self) -> int:
+        return self._config.num_hidden_layers
+
+    @property
+    def model_dim(self) -> int:
+        return self._config.hidden_size
+
+    @property
+    def vocab_size(self) -> int:
+        return self._config.vocab_size
+
+    @property
+    def head_size(self) -> int:
+        return self.model_dim // self.n_heads
+
+    @property
+    def n_heads(self) -> int:
+        return self._config.num_attention_heads
+
+    @property
+    def intermediate_dim(self) -> int:
+        return self._config.intermediate_size
+
+    @property
+    def n_heads_kv(self) -> int:
+        return self._config.num_key_value_heads
+
+    @property
+    def activation_dtype(self) -> DtypeEnum:
+        if self._config.torch_dtype == torch.float16:
+            return DtypeEnum.fp16
+        elif self._config.torch_dtype == torch.bfloat16:
+            return DtypeEnum.bf16
+        else:
+            raise NotImplementedError("Only fp16 and bf16 are supported")
+
+    @property
+    def mlp_activation_fn(self) -> ActivationType:
+        return ActivationType.GELU
+
+    @property
+    def norm_type(self) -> NormTypeEnum:
+        return NormTypeEnum.LayerNorm
+
+    @property
+    def positional_embedding_type(self) -> PositionalEmbeddingType:
+        return PositionalEmbeddingType.rotate_half
+
+    @property
+    def positional_embedding_config(self) -> Optional[RotateHalfConfig]:
+        rotary_dim = int(self._config.partial_rotary_factor * self.head_size)
+        return RotateHalfConfig(rotate_dim=rotary_dim, theta_base=self._config.rope_theta)
+
+    """
+    Forward implementations
+    """
+
+    def _forward_embed(self, ragged_batch: RaggedBatchWrapper) -> torch.Tensor:
+        """
+        Performs the embedding lookup prior to running the transformer of the model.
+
+        Arguments:
+            ragged_batch (RaggedBatchWrapper): The batch to embed.
+
+        Returns:
+            torch.Tensor: The embedded batch.
+        """
+        embed = self.embed(ragged_batch, self._non_transformer.word_emb)
+
+        if embed.shape[-1] != self.model_dim:
+            raise ValueError(f"Embedding output shape {embed.shape} does not match model_dim {self.model_dim}")
+
+        return embed
+
+    def _forward_transformer_layer(self, layer_idx: int, residual: torch.Tensor, hidden_states: torch.Tensor,
+                                   ragged_batch_info: RaggedBatchWrapper) -> Tuple[torch.Tensor, torch.Tensor]:
+        """
+        Executes one (slightly offset) layer of the transformer. This implementation does a peak-ahead
+        optimization to fuse the layer norm of the next layer into the current layer.
+
+        Arguments:
+            layer_idx (int): The index of the layer to execute.
+            residual (torch.Tensor): The residual tensor from the previous layer.
+            hidden_states (torch.Tensor): The hidden states from the previous layer. This is the
+                hidden states after pre normalization.
+            ragged_batch_info (RaggedBatchWrapper): The batch metadata.
+        """
+        cur_params = self._transformer[layer_idx]
+        kv_cache = self.state_manager.get_cache(layer_idx)
+
+        attn_ln_out = hidden_states
+        attn_hidden_state = self.qkv(attn_ln_out, cur_params.qkv_w, b=cur_params.qkv_b)
+        attn_hidden_state = self.attn(attn_hidden_state, kv_cache, ragged_batch_info)
+        attention_output = self.attn_out(attn_hidden_state, cur_params.attn_out_w, b=cur_params.attn_out_b)
+
+        mlp_ln_out = hidden_states
+        mlp_hidden_state = self.mlp_1(mlp_ln_out, cur_params.mlp_1_w, b=cur_params.mlp_1_b)
+        mlp_output = self.mlp_2(mlp_hidden_state, cur_params.mlp_2_w, b=cur_params.mlp_2_b)
+
+        mlp_output.add_(attention_output)
+
+        if self.tp_size > 1:
+            dist.all_reduce(mlp_output, group=self._base_mp_group)
+
+        if layer_idx != self.num_layers - 1:
+            next_params = self._transformer[layer_idx + 1]
+            residual, mlp_output = self.norm(residual, mlp_output, next_params.ln_gamma, beta=next_params.ln_beta)
+        else:
+            # On last layer, we just need to perform the residual add. Adding into the residual
+            # here is safe.
+            residual.add_(mlp_output)
+
+        return residual, mlp_output
+
+    def _forward_unembed(self, hidden_states: torch.Tensor, ragged_batch_info: RaggedBatchWrapper) -> torch.Tensor:
+        """
+        Performs unembedding of the hidden states to logits. This will only sample the final
+        token of each sequence.
+        """
+        logits = self.unembed(hidden_states,
+                              self._non_transformer.word_unembed_w,
+                              ragged_batch_info,
+                              bias=self._non_transformer.word_unembed_b,
+                              gamma=self._non_transformer.final_norm_gamma,
+                              beta=self._non_transformer.final_norm_beta)
+
+        if self.tp_size > 1:
+            comm_buffer = empty_from(self._comm_logits, (self.tp_size, logits.shape[0], logits.shape[1]))
+            full_logits = empty_from(self._return_logits, (logits.shape[0], self.vocab_size))
+
+            dist.all_gather_into_tensor(comm_buffer, logits, group=self._base_mp_group)
+
+            full_logits.copy_(comm_buffer.permute(1, 0, 2).reshape(logits.shape[0], self.vocab_size))
+
+            return full_logits
+        else:
+            return logits
+
+    def forward(self, wrapped_batch: RaggedBatchWrapper) -> torch.Tensor:
+        residual = self._forward_embed(wrapped_batch)
+
+        residual, hidden_states = self.norm(residual,
+                                            None,
+                                            gamma=self._transformer[0].ln_gamma,
+                                            beta=self._transformer[0].ln_beta)
+
+        for layer_idx in range(self.num_layers):
+            residual, hidden_states = self._forward_transformer_layer(layer_idx, residual, hidden_states,
+                                                                      wrapped_batch)
+
+        return self._forward_unembed(residual, wrapped_batch)
@@ -0,0 +1,32 @@
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+from typing import Any
+
+from ...config_v2 import RaggedInferenceEngineConfig
+from ..inference_policy_base import ContainerMap, InferenceV2Policy
+from .containers import PhiNonTransformerContainer, PhiTransformerContainer
+from .model import PhiInferenceModel
+
+
+class PhiPolicy(InferenceV2Policy):
+
+    def instantiate_model(self, engine_config: RaggedInferenceEngineConfig, mp_group: Any) -> PhiInferenceModel:
+        return PhiInferenceModel(config=self._model_config, engine_config=engine_config, base_mp_group=mp_group)
+
+    def build_container_map(self) -> ContainerMap:
+        map = ContainerMap()
+
+        trans_container_cls = PhiTransformerContainer
+        transformer_containers = [trans_container_cls(self.model) for _ in range(self.model.num_layers)]
+
+        map.set_transformer_params(['model.layers'], transformer_containers)
+
+        map.set_non_transformer_params(PhiNonTransformerContainer(self.model))
+
+        map.set_unmapped_params(
+            [f'model.layers.{i}.self_attn.rotary_emb.inv_freq' for i in range(self.model.num_layers)])
+
+        return map