renderers 0.1.12.dev20__tar.gz → 0.1.13.dev5__tar.gz

{renderers-0.1.12.dev20 → renderers-0.1.13.dev5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: renderers
-Version: 0.1.12.dev20
+Version: 0.1.13.dev5
 Summary: Chat template renderers — deterministic message-to-token conversion for LLM training
 License-Expression: Apache-2.0
 License-File: LICENSE
@@ -114,7 +114,7 @@ next_prompt_ids = r.bridge_to_next_turn(
 )
 ```
 
-Hand-coded renderers ship for `qwen3`, `qwen3-vl`, `qwen3.5`, `qwen3.6`, `qwen3.8`, `gemma4`, `glm-5`, `glm-5.1`, `glm-5.3`, `glm-4.5`, `minimax-m2`, `deepseek-v3`, `deepseek-r1`, `deepseek-v4` (V4 Flash 0731), `kimi-k2`, `kimi-k2.5` / `kimi-k2.6`, `laguna-xs.2`, `laguna-xs-2.1`, `laguna-s-2.1`, `laguna-m.1`, `nemotron-3`, `nemotron-3-ultra`, `nemotron-3.5`, `llama-3`, `gpt-oss`, `hy3`, `inkling` / `inkling-small`, and `prime-qwen3`. Anything else falls back to `DefaultRenderer`, a generic `apply_chat_template` wrapper. `qwen3-vl`, `qwen3.5`, `qwen3.6`, `qwen3.8`, `gemma4`, `kimi-k2.5` / `kimi-k2.6`, and the Inkling checkpoints are multimodal (Inkling handles both image **and** audio).
+Hand-coded renderers ship for `qwen3`, `qwen3-vl`, `qwen3.5`, `qwen3.6`, `qwen3.8`, `gemma4`, `glm-5`, `glm-5.1`, `glm-5.3`, `glm-5.3-flash`, `glm-4.5`, `minimax-m2`, `deepseek-v3`, `deepseek-r1`, `deepseek-v4` (V4 Flash 0731), `kimi-k2`, `kimi-k2.5` / `kimi-k2.6`, `laguna-xs.2`, `laguna-xs-2.1`, `laguna-s-2.1`, `laguna-m.1`, `nemotron-3`, `nemotron-3-ultra`, `nemotron-3.5`, `llama-3`, `gpt-oss`, `hy3`, `inkling` / `inkling-small`, and `prime-qwen3`. Anything else falls back to `DefaultRenderer`, a generic `apply_chat_template` wrapper. `qwen3-vl`, `qwen3.5`, `qwen3.6`, `qwen3.8`, `gemma4`, `glm-5.3-flash`, `kimi-k2.5` / `kimi-k2.6`, and the Inkling checkpoints are multimodal (Inkling handles both image **and** audio; `glm-5.3-flash` renders images only with `process_multimodal=False`).
 
 ## API
 

{renderers-0.1.12.dev20 → renderers-0.1.13.dev5}/README.md

@@ -94,7 +94,7 @@ next_prompt_ids = r.bridge_to_next_turn(
 )
 ```
 
-Hand-coded renderers ship for `qwen3`, `qwen3-vl`, `qwen3.5`, `qwen3.6`, `qwen3.8`, `gemma4`, `glm-5`, `glm-5.1`, `glm-5.3`, `glm-4.5`, `minimax-m2`, `deepseek-v3`, `deepseek-r1`, `deepseek-v4` (V4 Flash 0731), `kimi-k2`, `kimi-k2.5` / `kimi-k2.6`, `laguna-xs.2`, `laguna-xs-2.1`, `laguna-s-2.1`, `laguna-m.1`, `nemotron-3`, `nemotron-3-ultra`, `nemotron-3.5`, `llama-3`, `gpt-oss`, `hy3`, `inkling` / `inkling-small`, and `prime-qwen3`. Anything else falls back to `DefaultRenderer`, a generic `apply_chat_template` wrapper. `qwen3-vl`, `qwen3.5`, `qwen3.6`, `qwen3.8`, `gemma4`, `kimi-k2.5` / `kimi-k2.6`, and the Inkling checkpoints are multimodal (Inkling handles both image **and** audio).
+Hand-coded renderers ship for `qwen3`, `qwen3-vl`, `qwen3.5`, `qwen3.6`, `qwen3.8`, `gemma4`, `glm-5`, `glm-5.1`, `glm-5.3`, `glm-5.3-flash`, `glm-4.5`, `minimax-m2`, `deepseek-v3`, `deepseek-r1`, `deepseek-v4` (V4 Flash 0731), `kimi-k2`, `kimi-k2.5` / `kimi-k2.6`, `laguna-xs.2`, `laguna-xs-2.1`, `laguna-s-2.1`, `laguna-m.1`, `nemotron-3`, `nemotron-3-ultra`, `nemotron-3.5`, `llama-3`, `gpt-oss`, `hy3`, `inkling` / `inkling-small`, and `prime-qwen3`. Anything else falls back to `DefaultRenderer`, a generic `apply_chat_template` wrapper. `qwen3-vl`, `qwen3.5`, `qwen3.6`, `qwen3.8`, `gemma4`, `glm-5.3-flash`, `kimi-k2.5` / `kimi-k2.6`, and the Inkling checkpoints are multimodal (Inkling handles both image **and** audio; `glm-5.3-flash` renders images only with `process_multimodal=False`).
 
 ## API
 

{renderers-0.1.12.dev20 → renderers-0.1.13.dev5}/docs/renderer-config.md

@@ -34,7 +34,7 @@ product in `tests/test_parity.py`.
 | Qwen3-VL | `Qwen3VLRendererConfig` | `add_vision_id` | `image_cache_max` |
 | Gemma 4 | `Gemma4RendererConfig` | `enable_thinking`, `preserve_thinking` | `image_cache_max` |
 | GLM-5 / 5.1 | `GLM5RendererConfig` / `GLM51RendererConfig` | `enable_thinking`, `clear_thinking` | - |
-| GLM-5.3 | `GLM53RendererConfig` | `clear_thinking`, `reasoning_effort` | - |
+| GLM-5.3 / 5.3 Flash | `GLM53RendererConfig` / `GLM53FlashRendererConfig` | `clear_thinking`, `reasoning_effort` | - |
 | GLM-4.5 | `GLM45RendererConfig` | `enable_thinking` | - |
 | gpt-oss | `GptOssRendererConfig` | `reasoning_effort`, `conversation_start_date` | `use_system_prompt`, `knowledge_cutoff`, `model_identity`, `auto_drop_analysis` |
 | Hy3 | `Hy3RendererConfig` | `reasoning_effort`, `preserved_thinking`, `is_training`, `raw_last_assistant`, `fallback_strategy` | - |
@@ -141,7 +141,7 @@ the knobs its template actually exposes:
 | Qwen3.8 | `preserve_thinking=True -> all`; else `enable_thinking=False -> all`; else `tool_cycle` |
 | Gemma 4 | `preserve_thinking=True -> all`; else `enable_thinking=False -> all`; else `tool_cycle` |
 | GLM-5 / 5.1 | `clear_thinking=False -> all`; else `enable_thinking=False -> all`; else `tool_cycle` |
-| GLM-5.3 | `clear_thinking=False -> all`, else `tool_cycle` |
+| GLM-5.3 / 5.3 Flash | `clear_thinking=False -> all`, else `tool_cycle` |
 | GLM-4.5 | `enable_thinking=False -> all`, else `tool_cycle` |
 | gpt-oss | `auto_drop_analysis=False -> all`, else `tool_cycle` |
 | Hy3 | `preserved_thinking=True -> all`, else `tool_cycle` |

{renderers-0.1.12.dev20 → renderers-0.1.13.dev5}/renderers/__init__.py

@@ -55,6 +55,7 @@ from renderers.configs import (
     GLM5RendererConfig,
     GLM45RendererConfig,
     GLM51RendererConfig,
+    GLM53FlashRendererConfig,
     GLM53RendererConfig,
     GptOssRendererConfig,
     Hy3RendererConfig,
@@ -95,6 +96,7 @@ _LAZY_RENDERERS: dict[str, str] = {
     "DefaultRenderer": "renderers.default",
     "GLM45Renderer": "renderers.glm45",
     "GLM51Renderer": "renderers.glm5",
+    "GLM53FlashRenderer": "renderers.glm5",
     "GLM53Renderer": "renderers.glm5",
     "GLM5Renderer": "renderers.glm5",
     "GptOssRenderer": "renderers.gpt_oss",
@@ -155,6 +157,8 @@ __all__ = [
     "GLM45RendererConfig",
     "GLM51Renderer",
     "GLM51RendererConfig",
+    "GLM53FlashRenderer",
+    "GLM53FlashRendererConfig",
     "GLM53Renderer",
     "GLM53RendererConfig",
     "GLM5Renderer",

{renderers-0.1.12.dev20 → renderers-0.1.13.dev5}/renderers/_version.py

@@ -18,7 +18,7 @@ version_tuple: tuple[int | str, ...]
 commit_id: str | None
 __commit_id__: str | None
 
-__version__ = version = '0.1.12.dev20'
-__version_tuple__ = version_tuple = (0, 1, 12, 'dev20')
+__version__ = version = '0.1.13.dev5'
+__version_tuple__ = version_tuple = (0, 1, 13, 'dev5')
 
 __commit_id__ = commit_id = None

{renderers-0.1.12.dev20 → renderers-0.1.13.dev5}/renderers/base.py

@@ -1012,6 +1012,8 @@ MODEL_RENDERER_MAP: dict[str, str] = {
     "zai-org/GLM-5.1": "glm-5.1",
     "zai-org/GLM-5.3": "glm-5.3",
     "zai-org/GLM-5.3-BF16": "glm-5.3",
+    "zai-org/GLM-5.3-Flash": "glm-5.3-flash",
+    "zai-org/GLM-5.3-Flash-BF16": "glm-5.3-flash",
     # GLM-4.5.
     "THUDM/GLM-4.5-Air": "glm-4.5",
     "zai-org/GLM-4.5-Air": "glm-4.5",
@@ -1353,7 +1355,12 @@ def _populate_registry():
     from renderers.deepseek_v4 import DeepSeekV4Renderer
     from renderers.default import DefaultRenderer
     from renderers.gemma4 import Gemma4Renderer
-    from renderers.glm5 import GLM5Renderer, GLM51Renderer, GLM53Renderer
+    from renderers.glm5 import (
+        GLM5Renderer,
+        GLM51Renderer,
+        GLM53FlashRenderer,
+        GLM53Renderer,
+    )
     from renderers.glm45 import GLM45Renderer
     from renderers.gpt_oss import GptOssRenderer
     from renderers.hy3 import Hy3Renderer
@@ -1393,6 +1400,7 @@ def _populate_registry():
             "glm-5": GLM5Renderer,
             "glm-5.1": GLM51Renderer,
             "glm-5.3": GLM53Renderer,
+            "glm-5.3-flash": GLM53FlashRenderer,
             "glm-4.5": GLM45Renderer,
             "minimax-m2": MiniMaxM2Renderer,
             "deepseek-v3": DeepSeekV3Renderer,

{renderers-0.1.12.dev20 → renderers-0.1.13.dev5}/renderers/client.py

@@ -7,6 +7,7 @@ messages → Renderer.render_ids() → token IDs → POST /inference/v1/generate
 from __future__ import annotations
 
 import asyncio
+import base64
 import json
 import logging
 import math
@@ -14,6 +15,7 @@ from collections.abc import Mapping
 from typing import Any, cast
 
 import httpx
+import numpy as np
 from openai import AsyncOpenAI
 
 from renderers.base import (
@@ -134,9 +136,26 @@ def parse_generate_response(raw: bytes) -> dict[str, Any]:
     return payload
 
 
+def _parse_packed_completion_logprobs(
+    packed: Mapping[str, Any], completion_ids: list[int]
+) -> list[float]:
+    """prime-rl's packed form: base64 float32 ``{data, shape, dtype}``, one per token."""
+    values = np.frombuffer(base64.b64decode(packed["data"]), dtype=packed["dtype"])
+    valid = np.isfinite(values) & (values > VLLM_LOGPROB_SENTINEL)
+    if len(values) != len(completion_ids) or not valid.all():
+        raise MalformedGenerateResponseError(
+            f"Engine response choice.completion_logprobs: {len(values)} values for "
+            f"{len(completion_ids)} completion tokens, or a non-finite or missing (-9999) logprob."
+        )
+    return values.astype(np.float64).tolist()
+
+
 def _parse_completion_logprobs(
     choice: Mapping[str, Any], completion_ids: list[int]
 ) -> list[float]:
+    packed = choice.get("completion_logprobs")
+    if packed is not None:
+        return _parse_packed_completion_logprobs(packed, completion_ids)
     raw_logprobs = choice.get("logprobs")
     if not isinstance(raw_logprobs, Mapping):
         raise MalformedGenerateResponseError(
@@ -317,7 +336,9 @@ async def generate(
         "token_ids": prompt_ids,
         "sampling_params": sp,
     }
-    content_parts = _content_parts(messages) if not process_multimodal else None
+    content_parts = (
+        _content_parts(messages, renderer=renderer) if not process_multimodal else None
+    )
     features = (
         _build_mm_features(renderer, mm_data)
         if process_multimodal and mm_data and not mm_data.is_empty()
@@ -376,7 +397,8 @@ async def generate(
 
     routed_experts = choice.get("routed_experts")
     # vLLM's native kept-set sampling masks (``--return-sampling-mask``):
-    # one list of surviving vocab ids per completion token.
+    # one list of surviving vocab ids per completion token, or (prime-rl's
+    # server) packed CSR ``{"ids", "counts"}`` base64 int32 arrays.
     sampling_mask = choice.get("sampling_mask")
 
     # /inference/v1/generate returns finish_reason in {"stop","length",...} —
@@ -434,8 +456,15 @@ _MEDIA_URL_TYPES = {
 }
 
 
-def _content_parts(messages: list[Message]) -> list[dict[str, Any]]:
+def _content_parts(
+    messages: list[Message], *, renderer: Renderer
+) -> list[dict[str, Any]]:
     """Flatten raw media in prompt order for vLLM's token generate endpoint."""
+    # Some templates reorder tool results. Use the same order for raw media,
+    # including when the caller supplies a prebuilt prompt and skips rendering.
+    order_messages = getattr(renderer, "messages_in_prompt_order", None)
+    if order_messages is not None:
+        messages = order_messages(messages)
     parts: list[dict[str, Any]] = []
     for message in messages:
         content = message.get("content")

{renderers-0.1.12.dev20 → renderers-0.1.13.dev5}/renderers/configs.py

@@ -434,6 +434,12 @@ class GLM53RendererConfig(BaseRendererConfig):
         return self
 
 
+class GLM53FlashRendererConfig(GLM53RendererConfig):
+    """GLM-5.3 Flash renderer config. GLM-5.3's template surface, plus images."""
+
+    name: Literal["glm-5.3-flash"] = "glm-5.3-flash"
+
+
 class GLM45RendererConfig(BaseRendererConfig):
     """GLM-4.5 Air renderer config."""
 
@@ -1042,6 +1048,7 @@ RendererConfig = Annotated[
         GLM5RendererConfig,
         GLM51RendererConfig,
         GLM53RendererConfig,
+        GLM53FlashRendererConfig,
         GLM45RendererConfig,
         GptOssRendererConfig,
         Hy3RendererConfig,
@@ -1091,6 +1098,7 @@ _CONFIG_BY_NAME: dict[str, type[BaseRendererConfig]] = {
     "glm-5": GLM5RendererConfig,
     "glm-5.1": GLM51RendererConfig,
     "glm-5.3": GLM53RendererConfig,
+    "glm-5.3-flash": GLM53FlashRendererConfig,
     "glm-4.5": GLM45RendererConfig,
     "gpt-oss": GptOssRendererConfig,
     "hy3": Hy3RendererConfig,
@@ -1144,6 +1152,7 @@ __all__ = [
     "DeepSeekV4RendererConfig",
     "GLM45RendererConfig",
     "GLM51RendererConfig",
+    "GLM53FlashRendererConfig",
     "GLM53RendererConfig",
     "GLM5RendererConfig",
     "Gemma4RendererConfig",