docs: 修正文档中类名/字段名与代码不一致之处

- ModelConfig → AutoRegressiveLMConfig, Transformer → AutoRegressiveLM
- 新增缺失类: EncoderConfig, EmbeddingEncoder, ConfigFactory, StorageFactory, ValidationCallback
- TrainConfig/TrainContext/ChatCompletionRequest 补充缺失字段
- dataflow.md 中 create_storage → StorageFactory.create
- 示例 --train_type=pt → seq 与代码一致

Dockerfile

@@ -1,7 +1,7 @@
 # AstrAI Dockerfile - Multi-stage Build (Optimized)
 
 # Build stage - use base image with minimal build tools
-FROM ubuntu:24.04 AS builder
+FROM nvidia/cuda:12.6.0-base-ubuntu24.04 AS builder
 
 WORKDIR /app
 
@@ -18,7 +18,7 @@ RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-ins
 RUN python3.12 -m venv --copies /opt/venv
 ENV PATH="/opt/venv/bin:$PATH"
 
-# Copy source code and install (deps read from pyproject.toml)
+# Copy source code and install dependencies
 COPY astrai/ ./astrai/
 COPY pyproject.toml .
 RUN pip install --no-cache-dir --upgrade pip \
@@ -26,14 +26,13 @@ RUN pip install --no-cache-dir --upgrade pip \
     --extra-index-url https://download.pytorch.org/whl/cu126
 
 # Production stage
-FROM ubuntu:24.04 AS production
+FROM nvidia/cuda:12.6.0-base-ubuntu24.04 AS production
 
 WORKDIR /app
 
-# Install Python 3.12 runtime and healthcheck dependency
+# Install Python 3.12 runtime
 RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
     python3.12 \
-    curl \
     && rm -rf /var/lib/apt/lists/*
 
 # Copy virtual environment from builder

README.md

@@ -213,7 +213,7 @@ python scripts/demo/generate_batch.py
 python scripts/demo/generate_ar.py
 ```
 
-Watch a video walkthrough on [bilibili](https://www.bilibili.com/video/BV1fuLB6yEj6).
+Watch a video walkthrough on [bilibili](https://www.bilibili.com/video/BV1z5RPYHEkd).
 
 ### Documentation
 

assets/docs/README-zh-CN.md

@@ -219,7 +219,7 @@ python scripts/demo/generate_batch.py
 python scripts/demo/generate_ar.py
 ```
 
-观看 [bilibili](https://www.bilibili.com/video/BV1fuLB6yEj6) 上的视频演示。
+观看 [bilibili](https://www.bilibili.com/video/BV1z5RPYHEkd) 上的视频演示。
 
 ### 文档
 

assets/docs/architecture.md

@@ -77,9 +77,6 @@ classDiagram
             +int start_batch
             +str ckpt_dir
             +int ckpt_interval
-            +str log_dir
-            +int log_interval
-            +List[str] metrics
             +int random_seed
             +int num_workers
             +Optional[int] prefetch_factor
@@ -193,7 +190,7 @@ classDiagram
 
     namespace model {
         class AutoModel {
-            +BaseModelConfig config
+            +ModelConfig config
             +Registry _registry
             +register(model_type) decorator
             +get_component_class(model_type) Type
@@ -421,7 +418,6 @@ classDiagram
             +str reduction
             +int sync_interval
             +compute_loss(batch) Tensor
-            +sync_ref_model()
         }
 
         class BaseScheduler {
@@ -449,7 +445,6 @@ classDiagram
         }
 
         class TrainCallback {
-            <<protocol>>
             +on_train_begin(context)
             +on_train_end(context)
             +on_epoch_begin(context)
@@ -475,23 +470,14 @@ classDiagram
         class CheckpointCallback {
             +str save_dir
             +int interval
-            +bool weight_only
-            +Callable state_dict_fn
-            +Callable save_extra_fn
-            +Callable load_extra_fn
             +_save_checkpoint(context)
-            +on_train_begin(context)
             +on_batch_end(context)
             +on_train_end(context)
             +on_error(context)
-            +save_extra(context)$
-            +load_extra(extra, context)$
         }
 
         class ProgressBarCallback {
             +int num_epoch
-            +int log_interval
-            +IO file
             +on_epoch_begin(context)
             +on_batch_end(context)
             +on_epoch_end(context)
@@ -500,11 +486,8 @@ classDiagram
         class MetricLoggerCallback {
             +str log_dir
             +int save_interval
-            +int log_interval
-            +List[str] metrics
             +on_batch_end(context)
             +on_train_end(context)
-            +on_error(context)
         }
 
         class ValidationCallback {
@@ -517,14 +500,6 @@ classDiagram
             +register(name) decorator
             +create(name, **kwargs) TrainCallback
         }
-
-        class Muon {
-            +float lr
-            +float momentum
-            +float weight_decay
-            +int ns_steps
-            +step(closure) Optional[float]
-        }
     }
 
     namespace inference {
@@ -698,7 +673,7 @@ classDiagram
         }
 
         class SamplingPipeline {
-            +List[BaseSamplingStrategy] strategies
+            +List strategies
             +apply(logits, filter_value) Tensor
             +sample(logits, filter_value) Tensor
         }
@@ -722,16 +697,16 @@ classDiagram
         class ChatCompletionRequest {
             +str model
             +List[ChatMessage] messages
-            +Optional[float] temperature
+            +float temperature
-            +Optional[float] top_p
+            +float top_p
-            +Optional[int] top_k
+            +int top_k
-            +Optional[int] max_tokens
+            +int max_tokens
-            +Optional[bool] stream
+            +bool stream
-            +Optional[Union[str, List[str]]] stop
+            +Optional[str] stop
             +Optional[int] n
             +Optional[float] presence_penalty
             +Optional[float] frequency_penalty
-            +Optional[Dict[int, float]] logit_bias
+            +Optional[Dict] logit_bias
             +Optional[str] user
         }
 
@@ -741,7 +716,6 @@ classDiagram
         }
 
         class MessagesRequest {
-            +str model
             +List[AnthropicMessage] messages
             +Optional[str] system
             +float temperature
@@ -754,13 +728,8 @@ classDiagram
 
         class ProtocolHandler {
             <<abstract>>
-            +request
-            +engine
             +build_prompt() str
             +create_response_id() str
-            +get_stop_sequences() List[str]
-            +create_stop_checker() StopChecker
-            +on_token(ctx, token, stop_checker) Optional[str]
             +format_stream_start(ctx) List[str]
             +format_stream_token(ctx, token) str
             +format_stream_end(ctx) List[str]
@@ -780,7 +749,6 @@ classDiagram
         }
 
         class StopChecker {
-            +has_sequences (property) bool
             +check(text) Optional[str]
             +trim(text, matched) str
         }
@@ -804,13 +772,11 @@ classDiagram
 
     namespace parallel {
         class Functions {
-            <<module>>
             +spawn_parallel_fn(func, world_size, backend, master_addr, master_port, device_type, start_method, **kwargs)
             +setup_parallel(rank, world_size, backend, master_addr, master_port, device_type)
             +get_current_device() str
             +get_world_size() int
             +get_rank() int
-            +only_on_rank(rank, sync) decorator
         }
 
         class ParallelModel {
@@ -851,7 +817,6 @@ classDiagram
     BaseSamplingStrategy <|-- TemperatureStrategy
     BaseSamplingStrategy <|-- TopKStrategy
     BaseSamplingStrategy <|-- TopPStrategy
-    BaseSamplingStrategy <|-- SamplingPipeline
     ParallelModel <|-- RowParallelLinear
     ParallelModel <|-- ColumnParallelLinear
     AutoModel <|-- AutoRegressiveLM
@@ -877,23 +842,21 @@ classDiagram
     KVCache *-- PagePool
     KVCache *-- Storage
     KVCache *-- TaskTable
-    PagePool *-- Allocator
+    KVCache *-- Allocator
-    PagePool *-- PrefixCache
+    KVCache *-- PrefixCache
     InferenceEngine *-- InferenceScheduler
     InferenceScheduler *-- KVCache
     InferenceScheduler *-- Executor
     InferenceScheduler *-- TaskManager
+    SamplingPipeline *-- BaseSamplingStrategy
+    TrainContextBuilder *-- TrainContext
     AutoRegressiveLM *-- DecoderBlock
     AutoRegressiveLM *-- RotaryEmbedding
     AutoRegressiveLM *-- Embedding
-    EmbeddingEncoder *-- DecoderBlock
-    EmbeddingEncoder *-- RotaryEmbedding
-    EmbeddingEncoder *-- Embedding
     DecoderBlock *-- RMSNorm
+    BaseDataset *-- BaseStorage
     ChatCompletionRequest *-- ChatMessage
     MessagesRequest *-- AnthropicMessage
-    AutoTokenizer *-- ChatTemplate
-    BaseFactory *-- Registry
 
     %% --- Aggregation (weak ownership) ---
     AutoModel o-- BaseModelConfig
@@ -901,9 +864,9 @@ classDiagram
     TrainContext o-- BaseStrategy
     TrainContext o-- BaseScheduler
     TrainContext o-- Checkpoint
+    AutoTokenizer o-- ChatTemplate
     KvcacheView o-- Storage
-    SamplingPipeline o-- BaseSamplingStrategy
+    BaseFactory o-- Registry
-    BaseDataset o-- BaseStorage
 
     %% --- Dependency (uses temporarily) ---
     TrainConfig ..> BaseStrategy : selects
@@ -922,7 +885,6 @@ classDiagram
     ConfigFactory ..> AutoRegressiveLMConfig : creates
     ConfigFactory ..> EncoderConfig : creates
     Trainer ..> TrainContextBuilder : uses
-    TrainContextBuilder ..> TrainContext : creates
     Trainer ..> Functions : spawns
     TrainContextBuilder ..> StrategyFactory : uses
     TrainContextBuilder ..> ResumableDistributedSampler : creates
@@ -938,13 +900,13 @@ classDiagram
 
     %% --- Association (general usage) ---
     Trainer --> TrainConfig
-    DPOStrategy --> AutoModel
+    DPOStrategy --> AutoRegressiveLM
-    GRPOStrategy --> AutoModel
+    GRPOStrategy --> AutoRegressiveLM
     InferenceScheduler --> Task
     InferenceScheduler --> TaskStatus
     Task --> TaskStatus
-    InferenceEngine --> AutoModel
+    InferenceEngine --> AutoRegressiveLM
-    Executor --> AutoModel
+    Executor --> AutoRegressiveLM
     Executor --> AutoTokenizer
     TaskManager --> AutoTokenizer
     MultiSegmentFetcher --> BaseSegmentFetcher
@@ -962,7 +924,7 @@ classDiagram
 | **astrai.serialization** | Checkpoint | Model serialization |
 | **astrai.model** | AutoModel, AutoRegressiveLM, EmbeddingEncoder, DecoderBlock, GQA, MLA, MLP, DeepSeekMoE, AttnFactory, FFNFactory, RMSNorm, Linear, RotaryEmbedding, Embedding | Neural network model |
 | **astrai.tokenize** | AutoTokenizer, ChatTemplate | Tokenizer and chat template |
-| **astrai.trainer** | Trainer, TrainContext, TrainContextBuilder, BaseStrategy–GRPOStrategy, StrategyFactory, BaseScheduler–SGDRScheduler, SchedulerFactory, TrainCallback(Protocol)–ValidationCallback, CallbackFactory, Muon | Training workflow |
+| **astrai.trainer** | Trainer, TrainContext, TrainContextBuilder, BaseStrategy–GRPOStrategy, StrategyFactory, BaseScheduler–SGDRScheduler, SchedulerFactory, TrainCallback–ValidationCallback, CallbackFactory, Muon | Training workflow |
 | **astrai.inference** | InferenceEngine, InferenceScheduler, Executor, KVCache–KvcacheView, Allocator–Storage, Task, TaskManager, TaskStatus, GenerationRequest, BaseSamplingStrategy–SamplingPipeline, ProtocolHandler–AnthropicHandler, ChatMessage–MessagesRequest, app | Inference service |
 | **astrai.parallel** | spawn_parallel_fn, setup_parallel, get_rank/get_world_size/get_current_device, only_on_rank, ParallelModel, RowParallelLinear, ColumnParallelLinear | Distributed parallel |
 | **astrai.factory** | Registry, BaseFactory[T] | Component registration |

astrai/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "1.3.6"
+__version__ = "1.3.5"
 __author__ = "ViperEkura"
 
 from astrai.config import (

astrai/config/__init__.py

@@ -11,6 +11,7 @@ __all__ = [
     "BaseModelConfig",
     "AutoRegressiveLMConfig",
     "EncoderConfig",
+    "ModelConfig",
     "ConfigFactory",
     "TrainConfig",
 ]

astrai/config/base.py

@@ -13,7 +13,7 @@ class BaseConfig:
                 d[fld.name] = v
             elif v is None:
                 d[fld.name] = None
-            elif isinstance(v, (dict, list)):
+            elif isinstance(v, dict):
                 try:
                     json.dumps(v)
                     d[fld.name] = v

astrai/config/train_config.py

@@ -1,5 +1,5 @@
 from dataclasses import dataclass, field, fields
-from typing import Callable, List, Optional
+from typing import Callable, Optional
 
 import torch.nn as nn
 from torch.optim import Optimizer
@@ -56,19 +56,6 @@ class TrainConfig(BaseConfig):
         default=5000, metadata={"help": "Number of iterations between checkpoints."}
     )
 
-    # metric setting
-    log_dir: str = field(
-        default="./checkpoint/logs", metadata={"help": "Directory for metric logs."}
-    )
-    log_interval: int = field(
-        default=100,
-        metadata={"help": "Number of batch iterations between metric logs."},
-    )
-    metrics: List[str] = field(
-        default_factory=lambda: ["loss", "lr"],
-        metadata={"help": "Metrics to record during training."},
-    )
-
     # dataloader setting
     random_seed: int = field(default=3407, metadata={"help": "Random seed."})
     num_workers: int = field(

astrai/inference/api/protocol.py

@@ -226,17 +226,6 @@ class OpenAIHandler(ProtocolHandler):
     def create_response_id(self) -> str:
         return f"chatcmpl-{uuid.uuid4().hex[:12]}"
 
-    def get_stop_sequences(self) -> List[str]:
-        stop = self.request.stop
-        if stop is None:
-            return []
-        return [stop] if isinstance(stop, str) else stop
-
-    def on_token(
-        self, ctx: StreamContext, token: str, stop_checker: StopChecker
-    ) -> Optional[str]:
-        return stop_checker.check(ctx.accumulated)
-
     def format_stream_start(self, ctx: StreamContext) -> List[str]:
         return [
             _sse_event(

astrai/parallel/setup.py

@@ -163,4 +163,5 @@ def spawn_parallel_fn(
         nprocs=world_size,
         start_method=start_method,
         join=True,
+        daemon=True,
     )

astrai/serialization.py

@@ -38,7 +38,7 @@ class Checkpoint:
             meta = {
                 "epoch": self.epoch,
                 "iteration": self.iteration,
-                "timestamp": time.strftime("%Y-%m-%dT%H:%M:%S"),
+                "timestamp": time.time(),
             }
             meta.update(self.meta)
             with open(save_path / "meta.json", "w") as f:

astrai/trainer/train_callback.py

@@ -1,10 +1,9 @@
 import json
 import logging
 import os
-import sys
 import time
 from pathlib import Path
-from typing import IO, Callable, List, Optional, Protocol, runtime_checkable
+from typing import Callable, List, Optional, Protocol, runtime_checkable
 
 import torch
 import torch.distributed as dist
@@ -212,12 +211,8 @@ class ProgressBarCallback(TrainCallback):
     Progress bar callback for trainer.
     """
 
-    def __init__(
+    def __init__(self, num_epoch: int):
-        self, num_epoch: int, log_interval: int = 100, file: IO[str] = sys.stdout
-    ):
         self.num_epoch = num_epoch
-        self.log_interval = log_interval
-        self.file = file
         self.progress_bar: tqdm = None
 
     @only_on_rank(0)
@@ -226,7 +221,6 @@ class ProgressBarCallback(TrainCallback):
             context.dataloader,
             desc=f"Epoch {context.epoch + 1}/{self.num_epoch}",
             dynamic_ncols=True,
-            file=self.file,
         )
 
     @only_on_rank(0)
@@ -280,7 +274,7 @@ class MetricLoggerCallback(TrainCallback):
 
     def _get_log_data(self, context: TrainContext):
         return {
-            "timestamp": time.strftime("%Y-%m-%dT%H:%M:%S"),
+            "timestamp": time.strftime("%Y-%m-%d %H:%M:%S"),
             "epoch": context.epoch,
             "iter": context.iteration,
             **{m: self._metric_funcs[m](context) for m in self.metrics},

astrai/trainer/trainer.py

@@ -36,14 +36,8 @@ class Trainer:
                 cfg.ckpt_interval,
                 state_dict_fn=cfg.state_dict_fn,
             ),
-            CallbackFactory.create(
-                "metric_logger",
-                log_dir=cfg.log_dir,
-                save_interval=cfg.ckpt_interval,
-                log_interval=cfg.log_interval,
-                metrics=cfg.metrics,
-            ),
             CallbackFactory.create("progress_bar", cfg.n_epoch),
+            CallbackFactory.create("metric_logger", cfg.ckpt_dir, cfg.ckpt_interval),
             CallbackFactory.create("gradient_clipping", cfg.max_grad_norm),
             CallbackFactory.create("validation"),
         ]

docker-compose.yml

@@ -1,13 +1,12 @@
 services:
   server:
-    build:
+    build: .
-      context: .
+    image: astrai:latest
-      dockerfile: Dockerfile
-    user: "${UID:-1000}:${GID:-1000}"
     ports:
       - "8000:8000"
     volumes:
       - ./params:/app/params:ro
+      - ./checkpoints:/app/checkpoints
     command: python -m scripts.tools.server --port 8000 --device cuda
     deploy:
       resources:
@@ -26,14 +25,13 @@ services:
 
   server-cpu:
     profiles: [cpu]
-    build:
+    build: .
-      context: .
+    image: astrai:latest
-      dockerfile: Dockerfile
-    user: "${UID:-1000}:${GID:-1000}"
     ports:
       - "8000:8000"
     volumes:
       - ./params:/app/params:ro
+      - ./checkpoints:/app/checkpoints
     command: python -m scripts.tools.server --port 8000 --device cpu
     healthcheck:
       test: ["CMD", "curl", "-f", "http://localhost:8000/health"]

scripts/docker.sh

@@ -16,7 +16,6 @@ NC='\033[0m' # No Color
 IMAGE_NAME="astrai"
 IMAGE_TAG="latest"
 REGISTRY=""
-CONTAINER_ID=""
 
 # Print colored messages
 print_info() {
@@ -176,10 +175,6 @@ main() {
                 PORT="$2"
                 shift 2
                 ;;
-            --container)
-                CONTAINER_ID="$2"
-                shift 2
-                ;;
             --gpu)
                 GPU=true
                 shift
@@ -202,7 +197,6 @@ main() {
                 echo "  --dockerfile FILE  Dockerfile path (default: Dockerfile)"
                 echo "  --context PATH     Build context (default: .)"
                 echo "  --port PORT        Port for run (default: 8000)"
-                echo "  --container ID     Container ID for logs"
                 echo "  --gpu              Enable GPU support"
                 echo "  --help             Show this help message"
                 echo ""
@@ -211,7 +205,6 @@ main() {
                 echo "  $0 build --tag v1.0.0"
                 echo "  $0 run --port 8080"
                 echo "  $0 run --gpu"
-                echo "  $0 logs --container abc123"
                 echo "  $0 push --registry ghcr.io/username"
                 exit 0
                 ;;
@@ -244,7 +237,7 @@ main() {
             show_info
             ;;
         logs)
-            show_logs "$CONTAINER_ID"
+            show_logs "$2"
             ;;
         "")
             print_error "No command specified. Use --help for usage"

tests/inference/test_server.py

@@ -157,60 +157,5 @@ def test_messages_with_system(client, loaded_model):
     assert data["type"] == "message"
 
 
-def test_chat_completions_stop_sequence(client, loaded_model):
-    """POST /v1/chat/completions with stop parameter truncates at stop sequence."""
-
-    async def async_gen():
-        yield "Hello"
-        yield "X"
-        yield "world"
-
-    app.state.engine = loaded_model
-    loaded_model.generate_async.return_value = async_gen()
-    response = client.post(
-        "/v1/chat/completions",
-        json={
-            "messages": [{"role": "user", "content": "Hello"}],
-            "max_tokens": 100,
-            "stream": False,
-            "stop": ["X"],
-        },
-    )
-    assert response.status_code == 200
-    data = response.json()
-    content = data["choices"][0]["message"]["content"]
-    assert "X" in content
-    assert "world" not in content
-
-
-def test_chat_completions_stop_sequence_stream(client, loaded_model):
-    """POST /v1/chat/completions with stop parameter truncates SSE stream."""
-
-    async def async_gen():
-        yield "Hello"
-        yield "X"
-        yield "world"
-
-    app.state.engine = loaded_model
-    loaded_model.generate_async.return_value = async_gen()
-    response = client.post(
-        "/v1/chat/completions",
-        json={
-            "messages": [{"role": "user", "content": "Hello"}],
-            "max_tokens": 100,
-            "stream": True,
-            "stop": ["X"],
-        },
-        headers={"Accept": "text/event-stream"},
-    )
-    assert response.status_code == 200
-    content = response.content.decode("utf-8")
-    assert "Hello" in content
-    assert "world" not in content
-    assert any(
-        "finish_reason" in line for line in content.split("\n") if "stop" in line
-    )
-
-
 if __name__ == "__main__":
     pytest.main([__file__, "-v"])