gpustack-runner 0.1.24__tar.gz → 0.1.24.post2__tar.gz

{gpustack_runner-0.1.24 → gpustack_runner-0.1.24.post2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gpustack-runner
-Version: 0.1.24
+Version: 0.1.24.post2
 Summary: GPUStack Runner is library for registering runnable accelerated backends and services in GPUStack.
 Project-URL: Homepage, https://github.com/gpustack/runner
 Project-URL: Bug Tracker, https://github.com/gpustack/gpustack/issues
@@ -46,24 +46,23 @@ The following table lists the supported accelerated backends and their correspon
 
 ### Ascend CANN
 
-> [!CAUTION]
-> Since v0.1.23:
-> - Deprecated MindIE `2.1.rc1`.
-
 > [!WARNING]
 > - The Atlas 300I series is currently experimental in vLLM, only supporting eager mode and float16 data type. And there
     are some known issues for running vLLM, you can refer to
     vllm-ascend [#3316](https://github.com/vllm-project/vllm-ascend/issues/3316)
     and [#2795](https://github.com/vllm-project/vllm-ascend/issues/2795).
 
-| CANN Version <br/> (Variant) | MindIE                   | vLLM                                                       | SGLang                 |
-|------------------------------|--------------------------|------------------------------------------------------------|------------------------|
-| 8.3 (A3/910C)                | `2.2.rc1`                | `0.13.0`, `0.12.0`, `0.11.0`                               | `0.5.7`, `0.5.6.post2` |
-| 8.3 (910B)                   | `2.2.rc1`                | `0.13.0`, `0.12.0`, `0.11.0`                               | `0.5.7`, `0.5.6.post2` |
-| 8.3 (310P)                   | `2.2.rc1`                |                                                            |                        |
-| 8.2 (A3/910C)                | `2.1.rc2`                | `0.10.2`, `0.10.1.1`                                       | `0.5.2`, `0.5.1.post3` |
-| 8.2 (910B)                   | `2.1.rc2`, ~~`2.1.rc1`~~ | `0.10.2`, `0.10.1.1`, <br/>`0.10.0`, `0.9.2`, <br/>`0.9.1` | `0.5.2`, `0.5.1.post3` |
-| 8.2 (310P)                   | `2.1.rc2`, ~~`2.1.rc1`~~ | `0.10.0`, `0.9.2`                                          |                        |
+| CANN Version <br/> (Variant) | MindIE    | vLLM                                                       | SGLang                 |
+|------------------------------|-----------|------------------------------------------------------------|------------------------|
+| 8.5 (A3/910C)                | `2.3.0`   | `0.14.1`, `0.13.0`                                         | `0.5.8`                |
+| 8.5 (910B)                   | `2.3.0`   | `0.14.1`, `0.13.0`                                         | `0.5.8`                |
+| 8.5 (310P)                   | `2.3.0`   | `0.14.1`                                                   |                        |
+| 8.3 (A3/910C)                | `2.2.rc1` | `0.12.0`, `0.11.0`                                         | `0.5.7`, `0.5.6.post2` |
+| 8.3 (910B)                   | `2.2.rc1` | `0.12.0`, `0.11.0`                                         | `0.5.7`, `0.5.6.post2` |
+| 8.3 (310P)                   | `2.2.rc1` |                                                            |                        |
+| 8.2 (A3/910C)                | `2.1.rc2` | `0.10.2`, `0.10.1.1`                                       | `0.5.2`, `0.5.1.post3` |
+| 8.2 (910B)                   | `2.1.rc2` | `0.10.2`, `0.10.1.1`, <br/>`0.10.0`, `0.9.2`, <br/>`0.9.1` | `0.5.2`, `0.5.1.post3` |
+| 8.2 (310P)                   | `2.1.rc2` | `0.10.0`, `0.9.2`                                          |                        |
 
 ### Iluvatar CoreX
 
@@ -73,13 +72,6 @@ The following table lists the supported accelerated backends and their correspon
 
 ### NVIDIA CUDA
 
-> [!CAUTION]
-> Since v0.1.23:
-> - Deprecated all services for CUDA 12.4.
-> - Deprecated vLLM `0.11.0`, `0.10.1.1`, `0.10.0`.
-> - Deprecated SGLang `0.5.5`.
-> - Deprecated VoxBox `0.0.20`.
-
 > [!NOTE]
 > - CUDA 12.9 supports Compute Capabilities:
     `7.5 8.0+PTX 8.9 9.0 10.0 10.3 12.0 12.1+PTX`.
@@ -88,12 +80,11 @@ The following table lists the supported accelerated backends and their correspon
 > - CUDA 12.6/12.4 supports Compute Capabilities:
     `7.5 8.0+PTX 8.9 9.0+PTX`.
 
-| CUDA Version <br/> (Variant) | vLLM                                                                                              | SGLang                                                                 | VoxBox                 |
-|------------------------------|---------------------------------------------------------------------------------------------------|------------------------------------------------------------------------|------------------------|
-| 12.9                         | `0.13.0`, `0.12.0`, <br/>`0.11.2`                                                                 | `0.5.7`, `0.5.6.post2`                                                 |                        |
-| 12.8                         | `0.13.0`, `0.12.0`, <br/>`0.11.2`, ~~`0.11.0`~~, <br/>`0.10.2`, ~~`0.10.1.1`~~, <br/>~~`0.10.0`~~ | `0.5.7`, `0.5.6.post2`, `0.5.5.post3`, <br/>~~`0.5.5`~~, `0.5.4.post3` | `0.0.21`, ~~`0.0.20`~~ |
-| 12.6                         | `0.13.0`, `0.12.0`, <br/>`0.11.2`, ~~`0.11.0`~~, <br/>`0.10.2`, ~~`0.10.1.1`~~, <br/>~~`0.10.0`~~ |                                                                        | `0.0.21`, ~~`0.0.20`~~ |
-| 12.4                         | ~~`0.11.0`~~, ~~`0.10.2`~~, <br/>~~`0.10.1.1`~~, ~~`0.10.0`~~                                     |                                                                        | ~~`0.0.20`~~           |
+| CUDA Version <br/> (Variant) | vLLM                                        | SGLang                                                    | VoxBox   |
+|------------------------------|---------------------------------------------|-----------------------------------------------------------|----------|
+| 12.9                         | `0.13.0`, `0.12.0`, <br/>`0.11.2`           | `0.5.7`, `0.5.6.post2`                                    |          |
+| 12.8                         | `0.13.0`, `0.12.0`, <br/>`0.11.2`, `0.10.2` | `0.5.7`, `0.5.6.post2`, <br/>`0.5.5.post3`, `0.5.4.post3` | `0.0.21` |
+| 12.6                         | `0.13.0`, `0.12.0`, <br/>`0.11.2`,`0.10.2`  |                                                           | `0.0.21` |
 
 ### Hygon DTK
 
@@ -101,7 +92,7 @@ The following table lists the supported accelerated backends and their correspon
 |-----------------------------|----------------------------|
 | 25.04                       | `0.11.0`, `0.9.2`, `0.8.5` |
 
-### THead HGGC
+### T-Head HGGC
 
 | HGGC Version <br/> (Variant) | vLLM     | SGLang  |
 |------------------------------|----------|---------|
@@ -109,10 +100,11 @@ The following table lists the supported accelerated backends and their correspon
 
 ### MetaX MACA
 
-| MACA Version <br/> (Variant) | vLLM     |
-|------------------------------|----------|
-| 3.2                          | `0.10.2` |
-| 3.0                          | `0.9.1`  |
+| MACA Version <br/> (Variant) | vLLM     | SGLang  |
+|------------------------------|----------|---------|
+| 3.3                          | `0.11.2` | `0.5.6` |
+| 3.2                          | `0.10.2` |         |
+| 3.0                          | `0.9.1`  |         |
 
 ### MThreads MUSA
 
@@ -123,29 +115,23 @@ The following table lists the supported accelerated backends and their correspon
 
 ### AMD ROCm
 
-> [!CAUTION]
-> Since v0.1.23:
-> - Deprecated all services for ROCm 6.3.
-> - Deprecated vLLM `0.11.0`.
-
 > [!NOTE]
 > - ROCm 7.0 supports LLVM targets:
     `gfx908 gfx90a gfx942 gfx950 gfx1030 gfx1100 gfx1101 gfx1200 gfx1201 gfx1150 gfx1151`.
-> - ROCm 6.4/6.3 supports LLVM targets:
+> - ROCm 6.4 supports LLVM targets:
     `gfx908 gfx90a gfx942 gfx1030 gfx1100`.
 
 > [!WARNING]
-> - ROCm 7.0 vLLM `0.11.2/0.11.0` are reusing the official ROCm 6.4 PyTorch 2.9 wheel package rather than a ROCm
-    7.0 specific PyTorch build. Although supports ROCm 7.0 in vLLM `0.11.2/0.11.0`, `gfx1150/gfx1151` are not supported yet.
+> - ROCm 7.0 vLLM `0.11.2` are reusing the official ROCm 6.4 PyTorch 2.9 wheel package rather than a ROCm
+    7.0 specific PyTorch build. Although supports ROCm 7.0 in vLLM `0.11.2`, `gfx1150/gfx1151` are not supported yet.
 > - ROCm 6.4 vLLM `0.13.0` supports `gfx903 gfx90a gfx942` only.
 > - ROCm 6.4 SGLang supports `gfx942` only.
 > - ROCm 7.0 SGLang supports `gfx950` only.
 
-| ROCm Version <br/> (Variant) | vLLM                                            | SGLang                                |
-|------------------------------|-------------------------------------------------|---------------------------------------|
-| 7.0                          | `0.13.0`, `0.12.0`, <br/>`0.11.2`, ~~`0.11.0`~~ | `0.5.7`, `0.5.6.post2`                |
-| 6.4                          | `0.13.0`, `0.12.0`, <br/>`0.11.2`, `0.10.2`     | `0.5.7`, `0.5.6.post2`, `0.5.5.post3` |
-| 6.3                          | ~~`0.10.1.1`~~, ~~`0.10.0`~~                    |                                       |
+| ROCm Version <br/> (Variant) | vLLM                                        | SGLang                                     |
+|------------------------------|---------------------------------------------|--------------------------------------------|
+| 7.0                          | `0.13.0`, `0.12.0`, <br/>`0.11.2`           | `0.5.7`, `0.5.6.post2`                     |
+| 6.4                          | `0.13.0`, `0.12.0`, <br/>`0.11.2`, `0.10.2` | `0.5.7`, `0.5.6.post2`, <br/>`0.5.5.post3` |
 
 ## Directory Structure
 

{gpustack_runner-0.1.24 → gpustack_runner-0.1.24.post2}/README.md

@@ -26,24 +26,23 @@ The following table lists the supported accelerated backends and their correspon
 
 ### Ascend CANN
 
-> [!CAUTION]
-> Since v0.1.23:
-> - Deprecated MindIE `2.1.rc1`.
-
 > [!WARNING]
 > - The Atlas 300I series is currently experimental in vLLM, only supporting eager mode and float16 data type. And there
     are some known issues for running vLLM, you can refer to
     vllm-ascend [#3316](https://github.com/vllm-project/vllm-ascend/issues/3316)
     and [#2795](https://github.com/vllm-project/vllm-ascend/issues/2795).
 
-| CANN Version <br/> (Variant) | MindIE                   | vLLM                                                       | SGLang                 |
-|------------------------------|--------------------------|------------------------------------------------------------|------------------------|
-| 8.3 (A3/910C)                | `2.2.rc1`                | `0.13.0`, `0.12.0`, `0.11.0`                               | `0.5.7`, `0.5.6.post2` |
-| 8.3 (910B)                   | `2.2.rc1`                | `0.13.0`, `0.12.0`, `0.11.0`                               | `0.5.7`, `0.5.6.post2` |
-| 8.3 (310P)                   | `2.2.rc1`                |                                                            |                        |
-| 8.2 (A3/910C)                | `2.1.rc2`                | `0.10.2`, `0.10.1.1`                                       | `0.5.2`, `0.5.1.post3` |
-| 8.2 (910B)                   | `2.1.rc2`, ~~`2.1.rc1`~~ | `0.10.2`, `0.10.1.1`, <br/>`0.10.0`, `0.9.2`, <br/>`0.9.1` | `0.5.2`, `0.5.1.post3` |
-| 8.2 (310P)                   | `2.1.rc2`, ~~`2.1.rc1`~~ | `0.10.0`, `0.9.2`                                          |                        |
+| CANN Version <br/> (Variant) | MindIE    | vLLM                                                       | SGLang                 |
+|------------------------------|-----------|------------------------------------------------------------|------------------------|
+| 8.5 (A3/910C)                | `2.3.0`   | `0.14.1`, `0.13.0`                                         | `0.5.8`                |
+| 8.5 (910B)                   | `2.3.0`   | `0.14.1`, `0.13.0`                                         | `0.5.8`                |
+| 8.5 (310P)                   | `2.3.0`   | `0.14.1`                                                   |                        |
+| 8.3 (A3/910C)                | `2.2.rc1` | `0.12.0`, `0.11.0`                                         | `0.5.7`, `0.5.6.post2` |
+| 8.3 (910B)                   | `2.2.rc1` | `0.12.0`, `0.11.0`                                         | `0.5.7`, `0.5.6.post2` |
+| 8.3 (310P)                   | `2.2.rc1` |                                                            |                        |
+| 8.2 (A3/910C)                | `2.1.rc2` | `0.10.2`, `0.10.1.1`                                       | `0.5.2`, `0.5.1.post3` |
+| 8.2 (910B)                   | `2.1.rc2` | `0.10.2`, `0.10.1.1`, <br/>`0.10.0`, `0.9.2`, <br/>`0.9.1` | `0.5.2`, `0.5.1.post3` |
+| 8.2 (310P)                   | `2.1.rc2` | `0.10.0`, `0.9.2`                                          |                        |
 
 ### Iluvatar CoreX
 
@@ -53,13 +52,6 @@ The following table lists the supported accelerated backends and their correspon
 
 ### NVIDIA CUDA
 
-> [!CAUTION]
-> Since v0.1.23:
-> - Deprecated all services for CUDA 12.4.
-> - Deprecated vLLM `0.11.0`, `0.10.1.1`, `0.10.0`.
-> - Deprecated SGLang `0.5.5`.
-> - Deprecated VoxBox `0.0.20`.
-
 > [!NOTE]
 > - CUDA 12.9 supports Compute Capabilities:
     `7.5 8.0+PTX 8.9 9.0 10.0 10.3 12.0 12.1+PTX`.
@@ -68,12 +60,11 @@ The following table lists the supported accelerated backends and their correspon
 > - CUDA 12.6/12.4 supports Compute Capabilities:
     `7.5 8.0+PTX 8.9 9.0+PTX`.
 
-| CUDA Version <br/> (Variant) | vLLM                                                                                              | SGLang                                                                 | VoxBox                 |
-|------------------------------|---------------------------------------------------------------------------------------------------|------------------------------------------------------------------------|------------------------|
-| 12.9                         | `0.13.0`, `0.12.0`, <br/>`0.11.2`                                                                 | `0.5.7`, `0.5.6.post2`                                                 |                        |
-| 12.8                         | `0.13.0`, `0.12.0`, <br/>`0.11.2`, ~~`0.11.0`~~, <br/>`0.10.2`, ~~`0.10.1.1`~~, <br/>~~`0.10.0`~~ | `0.5.7`, `0.5.6.post2`, `0.5.5.post3`, <br/>~~`0.5.5`~~, `0.5.4.post3` | `0.0.21`, ~~`0.0.20`~~ |
-| 12.6                         | `0.13.0`, `0.12.0`, <br/>`0.11.2`, ~~`0.11.0`~~, <br/>`0.10.2`, ~~`0.10.1.1`~~, <br/>~~`0.10.0`~~ |                                                                        | `0.0.21`, ~~`0.0.20`~~ |
-| 12.4                         | ~~`0.11.0`~~, ~~`0.10.2`~~, <br/>~~`0.10.1.1`~~, ~~`0.10.0`~~                                     |                                                                        | ~~`0.0.20`~~           |
+| CUDA Version <br/> (Variant) | vLLM                                        | SGLang                                                    | VoxBox   |
+|------------------------------|---------------------------------------------|-----------------------------------------------------------|----------|
+| 12.9                         | `0.13.0`, `0.12.0`, <br/>`0.11.2`           | `0.5.7`, `0.5.6.post2`                                    |          |
+| 12.8                         | `0.13.0`, `0.12.0`, <br/>`0.11.2`, `0.10.2` | `0.5.7`, `0.5.6.post2`, <br/>`0.5.5.post3`, `0.5.4.post3` | `0.0.21` |
+| 12.6                         | `0.13.0`, `0.12.0`, <br/>`0.11.2`,`0.10.2`  |                                                           | `0.0.21` |
 
 ### Hygon DTK
 
@@ -81,7 +72,7 @@ The following table lists the supported accelerated backends and their correspon
 |-----------------------------|----------------------------|
 | 25.04                       | `0.11.0`, `0.9.2`, `0.8.5` |
 
-### THead HGGC
+### T-Head HGGC
 
 | HGGC Version <br/> (Variant) | vLLM     | SGLang  |
 |------------------------------|----------|---------|
@@ -89,10 +80,11 @@ The following table lists the supported accelerated backends and their correspon
 
 ### MetaX MACA
 
-| MACA Version <br/> (Variant) | vLLM     |
-|------------------------------|----------|
-| 3.2                          | `0.10.2` |
-| 3.0                          | `0.9.1`  |
+| MACA Version <br/> (Variant) | vLLM     | SGLang  |
+|------------------------------|----------|---------|
+| 3.3                          | `0.11.2` | `0.5.6` |
+| 3.2                          | `0.10.2` |         |
+| 3.0                          | `0.9.1`  |         |
 
 ### MThreads MUSA
 
@@ -103,29 +95,23 @@ The following table lists the supported accelerated backends and their correspon
 
 ### AMD ROCm
 
-> [!CAUTION]
-> Since v0.1.23:
-> - Deprecated all services for ROCm 6.3.
-> - Deprecated vLLM `0.11.0`.
-
 > [!NOTE]
 > - ROCm 7.0 supports LLVM targets:
     `gfx908 gfx90a gfx942 gfx950 gfx1030 gfx1100 gfx1101 gfx1200 gfx1201 gfx1150 gfx1151`.
-> - ROCm 6.4/6.3 supports LLVM targets:
+> - ROCm 6.4 supports LLVM targets:
     `gfx908 gfx90a gfx942 gfx1030 gfx1100`.
 
 > [!WARNING]
-> - ROCm 7.0 vLLM `0.11.2/0.11.0` are reusing the official ROCm 6.4 PyTorch 2.9 wheel package rather than a ROCm
-    7.0 specific PyTorch build. Although supports ROCm 7.0 in vLLM `0.11.2/0.11.0`, `gfx1150/gfx1151` are not supported yet.
+> - ROCm 7.0 vLLM `0.11.2` are reusing the official ROCm 6.4 PyTorch 2.9 wheel package rather than a ROCm
+    7.0 specific PyTorch build. Although supports ROCm 7.0 in vLLM `0.11.2`, `gfx1150/gfx1151` are not supported yet.
 > - ROCm 6.4 vLLM `0.13.0` supports `gfx903 gfx90a gfx942` only.
 > - ROCm 6.4 SGLang supports `gfx942` only.
 > - ROCm 7.0 SGLang supports `gfx950` only.
 
-| ROCm Version <br/> (Variant) | vLLM                                            | SGLang                                |
-|------------------------------|-------------------------------------------------|---------------------------------------|
-| 7.0                          | `0.13.0`, `0.12.0`, <br/>`0.11.2`, ~~`0.11.0`~~ | `0.5.7`, `0.5.6.post2`                |
-| 6.4                          | `0.13.0`, `0.12.0`, <br/>`0.11.2`, `0.10.2`     | `0.5.7`, `0.5.6.post2`, `0.5.5.post3` |
-| 6.3                          | ~~`0.10.1.1`~~, ~~`0.10.0`~~                    |                                       |
+| ROCm Version <br/> (Variant) | vLLM                                        | SGLang                                     |
+|------------------------------|---------------------------------------------|--------------------------------------------|
+| 7.0                          | `0.13.0`, `0.12.0`, <br/>`0.11.2`           | `0.5.7`, `0.5.6.post2`                     |
+| 6.4                          | `0.13.0`, `0.12.0`, <br/>`0.11.2`, `0.10.2` | `0.5.7`, `0.5.6.post2`, <br/>`0.5.5.post3` |
 
 ## Directory Structure
 

{gpustack_runner-0.1.24 → gpustack_runner-0.1.24.post2}/gpustack_runner/_version.py

@@ -27,8 +27,8 @@ version_tuple: VERSION_TUPLE
 __commit_id__: COMMIT_ID
 commit_id: COMMIT_ID
 
-__version__ = version = '0.1.24'
-__version_tuple__ = version_tuple = (0, 1, 24)
+__version__ = version = '0.1.24.post2'
+__version_tuple__ = version_tuple = (0, 1, 24, 'post2')
 try:
     from ._version_appendix import git_commit
     __commit_id__ = commit_id = git_commit

gpustack_runner-0.1.24.post2/gpustack_runner/_version_appendix.py

@@ -0,0 +1 @@
+git_commit = "62d75c6"

{gpustack_runner-0.1.24 → gpustack_runner-0.1.24.post2}/gpustack_runner/cmds/images.py

@@ -464,7 +464,7 @@ class SaveImagesSubCommand(SubCommand):
             # Submit tasks
             for task_name, src_img, dst_file, dst_file_relative in saving_tasks:
                 if dst_file.exists():
-                    print(f"{dst_file.name} already exists, skipping save {src_img}.")
+                    print(f"✅ {dst_file} already exists, skipping save {src_img}.")
                     continue
                 dst_file.parent.mkdir(parents=True, exist_ok=True, mode=0o744)
 
@@ -976,7 +976,7 @@ class LoadImagesSubCommand(SubCommand):
         load_parser.add_argument(
             "input",
             nargs=OPTIONAL,
-            help="Input directory to load images (default: current working directory)",
+            help="Input directory to load images from (default: current working directory)",
         )
 
         load_parser.set_defaults(func=LoadImagesSubCommand)
@@ -1348,10 +1348,6 @@ def list_images(**kwargs) -> list[PlatformedImage]:
         A list of platformed images.
 
     """
-    # Reset to default for listing images,
-    # in case the env is set to other value.
-    envs.GPUSTACK_RUNNER_DEFAULT_CONTAINER_NAMESPACE = None
-
     platform = kwargs.pop("platform", None)
     repository = kwargs.pop("repository", None)
 
@@ -1497,8 +1493,3 @@ def _execute_command(
             args=command,
             returncode=returncode,
         )
-
-
-append_images(
-    "gpustack/runtime:pause",
-)

{gpustack_runner-0.1.24 → gpustack_runner-0.1.24.post2}/gpustack_runner/runner.py

@@ -10,8 +10,6 @@ from typing import Any
 
 from dataclasses_json import dataclass_json
 
-from . import envs
-
 _RE_DOCKER_IMAGE = re.compile(
     r"(?:(?P<prefix>[\w\\.\-]+(?:/[\w\\.\-]+)*)/)?runner:(?P<backend>(Host|cann|corex|cuda|dtk|hggc|maca|musa|rocm))(?P<backend_version>[XY\d\\.]+)(?:-(?P<backend_variant>\w+))?-(?P<service>(vllm|voxbox|mindie|sglang))(?P<service_version>[\w\\.]+)(?:-(?P<suffix>\w+))?",
 )
@@ -239,10 +237,6 @@ def list_runners(**kwargs) -> Runners | list[dict]:
         json_list = json.load(f)
         runners = []
         for item in json_list:
-            if namespace := envs.GPUSTACK_RUNNER_DEFAULT_CONTAINER_NAMESPACE:
-                docker_image = item["docker_image"]
-                docker_image = docker_image.replace("gpustack/", f"{namespace}/")
-                item["docker_image"] = docker_image
             runners.append(Runner.from_dict(item))
 
     todict = kwargs.pop("todict", False)