[None][feat] Upgrade NIXL to v1.0.1 and UCX to 1.21 - #14436
Conversation
|
/bot run --stage-list "Build-Docker-Images" |
|
PR_Github #49828 [ run ] triggered by Bot. Commit: |
|
/bot run --disable-fail-fast |
|
PR_Github #49878 [ run ] triggered by Bot. Commit: |
|
PR_Github #49828 [ run ] completed with state |
bc7fa6a to
fe0819d
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #49928 [ run ] triggered by Bot. Commit: |
|
PR_Github #49878 [ run ] completed with state |
|
PR_Github #49928 [ run ] completed with state
|
1e35d2e to
c313620
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #50134 [ run ] triggered by Bot. Commit: |
73bf439 to
d349f77
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #50181 [ run ] triggered by Bot. Commit: |
|
PR_Github #50134 [ run ] completed with state |
|
PR_Github #50181 [ run ] completed with state
|
fd3fd7d to
b99939c
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #50290 [ run ] triggered by Bot. Commit: |
53f9a8b to
1ac7b73
Compare
|
/bot kill |
|
/bot run --disable-fail-fast |
|
PR_Github #50416 [ run ] triggered by Bot. Commit: |
|
PR_Github #50416 [ run ] completed with state
|
d86a652 to
e5fd61b
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #50512 [ run ] triggered by Bot. Commit: |
|
PR_Github #50512 [ run ] completed with state
|
e5fd61b to
8802bbf
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #50647 [ run ] triggered by Bot. Commit: |
|
PR_Github #50647 [ run ] completed with state
|
Squashed from upstream PR NVIDIA#13841 (NVIDIA/TensorRT-LLM): - Upgrade NIXL to v1.0.1 - Upgrade UCX to 1.21 - install_ucx.sh: replace pre-existing UCX with symlink - Add lib/ucx into libenv for CI PackageSanityCheck - Update images - Fix transfer bug Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
8802bbf to
9fec05e
Compare
|
/bot run --disable-fail-fast |
|
PR_Github #50922 [ run ] triggered by Bot. Commit: |
|
PR_Github #50922 [ run ] completed with state |
yuanjingx87
left a comment
There was a problem hiding this comment.
approved on behalf of trt-llm-oss-compliance
The trtllm dev environment used to install the meta `nixl` package, which provides a top-level `nixl/__init__.py` shim that redirects to `nixl_cu13` / `nixl_cu12`. After NVIDIA#14436 switched the dependency to `nixl-cu13` directly, the meta shim is no longer present, so `from nixl import nixl_agent, ...` in `tensorrt_llm/_torch/disaggregation/nixl/_agent_py.py` raises `ModuleNotFoundError: No module named 'nixl'` at import time, which in turn breaks `test_agent_multi_backends::test_run_with_different_env[1]` during collection of the spawned subprocess pytest. Resolve the symbols from `nixl_cu13` (or `nixl_cu12`) first and fall back to the meta-package only when neither CUDA-specific package is installed. Signed-off-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
The trtllm dev environment used to install the meta `nixl` package, which provides a top-level `nixl/__init__.py` shim that redirects to `nixl_cu13` / `nixl_cu12`. After NVIDIA#14436 switched the dependency to `nixl-cu13` directly, the meta shim is no longer present, so `from nixl import nixl_agent, ...` in `tensorrt_llm/_torch/disaggregation/nixl/_agent_py.py` raises `ModuleNotFoundError: No module named 'nixl'` at import time, which in turn breaks `test_agent_multi_backends::test_run_with_different_env[1]` during collection of the spawned subprocess pytest. Resolve the symbols from `nixl_cu13` (or `nixl_cu12`) first and fall back to the meta-package only when neither CUDA-specific package is installed. Signed-off-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
The trtllm dev environment used to install the meta `nixl` package, which provides a top-level `nixl/__init__.py` shim that redirects to `nixl_cu13` / `nixl_cu12`. After NVIDIA#14436 switched the dependency to `nixl-cu13` directly, the meta shim is no longer present, so `from nixl import nixl_agent, ...` in `tensorrt_llm/_torch/disaggregation/nixl/_agent_py.py` raises `ModuleNotFoundError: No module named 'nixl'` at import time, which in turn breaks `test_agent_multi_backends::test_run_with_different_env[1]` during collection of the spawned subprocess pytest. Resolve the symbols from `nixl_cu13` (or `nixl_cu12`) first and fall back to the meta-package only when neither CUDA-specific package is installed. Signed-off-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
The trtllm dev environment used to install the meta `nixl` package, which provides a top-level `nixl/__init__.py` shim that redirects to `nixl_cu13` / `nixl_cu12`. After NVIDIA#14436 switched the dependency to `nixl-cu13` directly, the meta shim is no longer present, so `from nixl import nixl_agent, ...` in `tensorrt_llm/_torch/disaggregation/nixl/_agent_py.py` raises `ModuleNotFoundError: No module named 'nixl'` at import time, which in turn breaks `test_agent_multi_backends::test_run_with_different_env[1]` during collection of the spawned subprocess pytest. Resolve the symbols from `nixl_cu13` (or `nixl_cu12`) first and fall back to the meta-package only when neither CUDA-specific package is installed. Signed-off-by: Shixiaowei02 <39303645+Shixiaowei02@users.noreply.github.com>
Squashed from upstream PR #13841 (NVIDIA/TensorRT-LLM):
Summary by CodeRabbit
Chores
Tests
Description
Test Coverage
PR Checklist
Please review the following before submitting your PR:
PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.
PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.
Test cases are provided for new code paths (see test instructions)
If PR introduces API changes, an appropriate PR label is added - either
api-compatibleorapi-breaking. Forapi-breaking, includeBREAKINGin the PR title.Any new dependencies have been scanned for license and vulnerabilities
CODEOWNERS updated if ownership changes
Documentation updated as needed
Update tava architecture diagram if there is a significant design change in PR.
The reviewers assigned automatically/manually are appropriate for the PR.
Please check this after reviewing the above items as appropriate for this PR.
GitHub Bot Help
To see a list of available CI bot commands, please comment
/bot help.