trtllm-flashinfer-upgrade

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

FlashInfer Version Upgrade Skill

FlashInfer版本升级技能

Automates upgrading the

flashinfer-python

package version across TensorRT-LLM.

自动完成TensorRT-LLM中

flashinfer-python

包版本的全仓库升级。

When to Use

使用场景

User asks to upgrade / bump / update flashinfer
Routine dependency update duty for flashinfer-python

用户要求升级/更新flashinfer
定期执行flashinfer-python的依赖更新任务

Prerequisites

前置条件

Step 0a: Determine GitHub Username

步骤0a：确定GitHub用户名

Query

gh

for the authenticated user's login:

bash

GITHUB_USERNAME=$(gh api user --jq .login)
echo "$GITHUB_USERNAME"

If this fails,

gh

is not authenticated — resolve Step 0c first, then retry. As a fallback, derive the username from the fork remote:

bash

GITHUB_USERNAME=$(git remote -v | grep -E 'github\.com/[^/]+/TensorRT-LLM' \
  | head -1 | sed -E 's|.*github\.com[:/]([^/]+)/TensorRT-LLM.*|\1|')

If neither works, ask the user via

AskUserQuestion

查询

gh

获取已认证用户的登录名：

bash

GITHUB_USERNAME=$(gh api user --jq .login)
echo "$GITHUB_USERNAME"

如果此命令失败，说明

gh

未认证——先解决步骤0c，然后重试。作为备选方案，从fork远程仓库推导用户名：

bash

GITHUB_USERNAME=$(git remote -v | grep -E 'github\.com/[^/]+/TensorRT-LLM' \
  | head -1 | sed -E 's|.*github\.com[:/]([^/]+)/TensorRT-LLM.*|\1|')

如果两种方法都无效，通过

AskUserQuestion

询问用户。

Step 0b: Verify Fork Remote

步骤0b：验证Fork远程仓库

Check that a git remote pointing to the user's fork of TensorRT-LLM exists:

bash

git remote -v | grep -E 'github\.com/${GITHUB_USERNAME}/TensorRT-LLM'

If no fork remote is found, stop and notify the user:

No GitHub fork remote detected. A fork of
NVIDIA/TensorRT-LLM
is required to push branches and create PRs.
Fork the repo at https://github.com/NVIDIA/TensorRT-LLM/fork
Add it as a git remote:
bash
git remote add fork https://github.com/<GITHUB_USERNAME>/TensorRT-LLM.git
Re-run this skill.

检查是否存在指向用户TensorRT-LLM fork的git远程仓库：

bash

git remote -v | grep -E 'github\.com/${GITHUB_USERNAME}/TensorRT-LLM'

如果未找到fork远程仓库，停止操作并通知用户：

未检测到GitHub fork远程仓库。需要
NVIDIA/TensorRT-LLM
的fork才能推送分支并创建PR。
在https://github.com/NVIDIA/TensorRT-LLM/fork处fork仓库
将其添加为git远程仓库：
bash
git remote add fork https://github.com/<GITHUB_USERNAME>/TensorRT-LLM.git
重新运行此技能。

Step 0c: Verify

gh

CLI Is Authenticated

步骤0c：验证

gh

CLI已认证

This skill uses the GitHub CLI (

gh

) to push branches and open PRs. Confirm it is installed and authenticated:

bash

gh auth status

Expected:

Logged in to github.com

with at least the

repo

scope.

repo

covers pushing to the user's fork and opening PRs on

NVIDIA/TensorRT-LLM

, so no separate fine-grained PATs are needed.

gh

reports "not logged in", instruct the user:

bash
gh auth login
Choose: GitHub.com → HTTPS → authenticate with a web browser (or paste a PAT with
repo
scope).

Note on
GH_CONFIG_DIR
: If the user keeps multiple

gh

accounts (e.g. a personal account and a separate account for

NVIDIA/TensorRT-LLM

work), they may point

gh

at a non-default config directory. Check

CLAUDE.local.md

AGENTS.md

or the environment for

GH_CONFIG_DIR

; if unclear, ask the user. When set, prefix every

gh

invocation:

GH_CONFIG_DIR=<path> gh ...

Do not proceed with the upgrade workflow until

gh auth status

is clean and the fork remote (Step 0b) is confirmed.

此技能使用GitHub CLI (

gh

)推送分支并创建PR。确认其已安装并完成认证：

bash

gh auth status

预期结果：

Logged in to github.com

且至少拥有

repo

权限。

repo

权限涵盖向用户fork推送代码以及在

NVIDIA/TensorRT-LLM

上创建PR，因此无需单独的细粒度PAT。

如果

gh

显示“未登录”，指导用户执行：

bash
gh auth login
选择：GitHub.com → HTTPS → 通过浏览器认证（或粘贴拥有
repo
权限的PAT）。

关于
GH_CONFIG_DIR
的说明：如果用户使用多个

gh

账户（例如个人账户和用于

NVIDIA/TensorRT-LLM

工作的独立账户），他们可能会将

gh

指向非默认配置目录。查看

CLAUDE.local.md

AGENTS.md

或环境变量中的

GH_CONFIG_DIR

；如果不确定，询问用户。设置后，在每个

gh

命令前添加前缀：

GH_CONFIG_DIR=<path> gh ...

。

在

gh auth status

显示正常且步骤0b中的fork远程仓库确认存在之前，不要继续升级流程。

Workflow

工作流程

Execute these steps in order. Use

AskUserQuestion

for user choices and

WebFetch

/ GitHub API for release data.

按顺序执行以下步骤。使用

AskUserQuestion

获取用户选择，使用

WebFetch

/GitHub API获取版本发布数据。

Step 1: Fetch Available Releases from GitHub

步骤1：从GitHub获取可用版本

Fetch the release list from

https://github.com/flashinfer-ai/flashinfer/releases

Use

WebFetch

with the URL

https://github.com/flashinfer-ai/flashinfer/releases

and extract all release tag names and dates. Collect both stable releases (e.g.,

v0.6.7

) and pre-release / nightly tags (e.g.,

v0.7.0.dev20260401

Alternatively, use the GitHub API via curl:

bash

curl -s "https://api.github.com/repos/flashinfer-ai/flashinfer/releases?per_page=30" \
  | python3 -c "
import json, sys
releases = json.load(sys.stdin)
for r in releases:
    tag = r['tag_name']
    pre = ' (pre-release)' if r['prerelease'] else ' (stable)'
    date = r['published_at'][:10]
    print(f'{tag}  {date}{pre}')
"

从

https://github.com/flashinfer-ai/flashinfer/releases

获取版本列表。

使用

WebFetch

访问URL

https://github.com/flashinfer-ai/flashinfer/releases

，提取所有版本标签名称和日期。收集稳定版本（例如

v0.6.7

）和预发布/夜间版本（例如

v0.7.0.dev20260401

）。

或者，通过curl调用GitHub API：

bash

curl -s "https://api.github.com/repos/flashinfer-ai/flashinfer/releases?per_page=30" \
  | python3 -c "
import json, sys
releases = json.load(sys.stdin)
for r in releases:
    tag = r['tag_name']
    pre = ' (pre-release)' if r['prerelease'] else ' (stable)'
    date = r['published_at'][:10]
    print(f'{tag}  {date}{pre}')
"

Step 2: Check Current Version

步骤2：检查当前版本

Read the current pinned version from

requirements.txt

bash

grep flashinfer-python requirements.txt

Expected format:

flashinfer-python==X.Y.Z

从

requirements.txt

读取当前固定版本：

bash

grep flashinfer-python requirements.txt

预期格式：

flashinfer-python==X.Y.Z

Step 3: Ask User Preferences

步骤3：询问用户偏好

Ask the user three questions using

AskUserQuestion

"Prefer a latest nightly release version?"
- Options: "Yes, show nightly/dev releases" | "No, stable releases only (Recommended)"
- This filters the release list shown in the next question.
"Which flashinfer-python version do you want to upgrade to?"
- Present up to 4 versions newer than the current version (filtered by the nightly preference above), with the latest as the recommended option.
- If the current version is already the latest, inform the user and stop.
"Also update
security_scanning/poetry.lock
?"
- Options: "No, skip the lockfile (Recommended)" | "Yes, update version + hashes"
- Default: No. The lockfile is typically regenerated by maintainers separately; editing it here can produce spurious hash diffs and stale
```
metadata.content-hash
```
  values.
- If the user answers Yes, follow the "Updating
```
security_scanning/poetry.lock
```
  hashes" subsection below; otherwise skip it entirely (do not touch
```
security_scanning/poetry.lock
```
  ).

使用

AskUserQuestion

向用户询问三个问题：

“是否偏好最新的夜间版本？”
- 选项：“是，显示夜间/开发版本” | “否，仅显示稳定版本（推荐）”
- 此选项将过滤下一个问题中显示的版本列表。
“你想要将flashinfer-python升级到哪个版本？”
- 展示最多4个比当前版本新的版本（根据上述夜间版本偏好过滤），并将最新版本设为推荐选项。
- 如果当前版本已是最新版本，通知用户并停止流程。
“是否同时更新
security_scanning/poetry.lock
？”
- 选项：“否，跳过锁文件（推荐）” | “是，更新版本和哈希值”
- 默认：否。锁文件通常由维护者单独重新生成；在此处编辑可能会产生虚假的哈希差异和过期的
```
metadata.content-hash
```
  值。
- 如果用户回答是，请遵循下面的“更新
```
security_scanning/poetry.lock
```
  哈希值”小节；否则完全跳过（不要修改
```
security_scanning/poetry.lock
```
  ）。

Step 4: Update All Version References

步骤4：更新所有版本引用

After the user selects a target version, update these files:

File	What to change	Always
`requirements.txt`	`flashinfer-python==OLD` → `flashinfer-python==NEW`	Yes
`security_scanning/pyproject.toml`	`"flashinfer-python (==OLD)"` → `"flashinfer-python (==NEW)"`	Yes
`ATTRIBUTIONS-Python.md`	`## flashinfer-python (OLD)` → `## flashinfer-python (NEW)`	Yes
`security_scanning/poetry.lock`	Update `version = "OLD"` → `version = "NEW"` under `[[package]] name = "flashinfer-python"` , and update the `files` list with new hashes	Only if user opted in at Step 3 question 3

用户选择目标版本后，更新以下文件：

文件	修改内容	是否必须
`requirements.txt`	`flashinfer-python==OLD` → `flashinfer-python==NEW`	是
`security_scanning/pyproject.toml`	`"flashinfer-python (==OLD)"` → `"flashinfer-python (==NEW)"`	是
`ATTRIBUTIONS-Python.md`	`## flashinfer-python (OLD)` → `## flashinfer-python (NEW)`	是
`security_scanning/poetry.lock`	更新 `[[package]] name = "flashinfer-python"` 下的 `version = "OLD"` → `version = "NEW"` ，并使用新哈希值更新 `files` 列表	仅当用户在步骤3的问题3中选择是时

Updating

security_scanning/poetry.lock

hashes

更新

security_scanning/poetry.lock

哈希值

Only perform this subsection if the user answered Yes to question 3 in Step 3. Otherwise skip it entirely.

The poetry.lock file contains SHA256 hashes for the wheel and sdist. Fetch them from PyPI:

bash

curl -s "https://pypi.org/pypi/flashinfer-python/NEW_VERSION/json" \
  | python3 -c "
import json, sys
data = json.load(sys.stdin)
for f in data['urls']:
    print(f'{f[\"filename\"]}  sha256:{f[\"digests\"][\"sha256\"]}')
"

Replace the old

files = [...]

block under

[[package]] name = "flashinfer-python"

with the new filenames and hashes. Also update the

[package.dependencies]

section if the new version has different dependencies (check PyPI JSON

requires_dist

Important: After manually editing both

security_scanning/pyproject.toml

and

security_scanning/poetry.lock

, the lockfile's

metadata.content-hash

becomes stale. Regenerate it by running:

bash

cd security_scanning && poetry lock --no-update && cd ..

This refreshes the hash without changing any other package versions. If

poetry

is available, you can alternatively use

poetry add flashinfer-python@NEW_VERSION

in the

security_scanning/

directory to update both

pyproject.toml

and

poetry.lock

automatically (including the content-hash).

仅当用户在步骤3的问题3中回答是时执行此小节。否则完全跳过。

poetry.lock文件包含wheel和sdist的SHA256哈希值。从PyPI获取这些值：

bash

curl -s "https://pypi.org/pypi/flashinfer-python/NEW_VERSION/json" \
  | python3 -c "
import json, sys
data = json.load(sys.stdin)
for f in data['urls']:
    print(f'{f[\"filename\"]}  sha256:{f[\"digests\"][\"sha256\"]}')
"

将

[[package]] name = "flashinfer-python"

下旧的

files = [...]

块替换为新的文件名和哈希值。如果新版本有不同的依赖项，请同时更新

[package.dependencies]

部分（查看PyPI JSON中的

requires_dist

）。

重要提示：手动编辑

security_scanning/pyproject.toml

和

security_scanning/poetry.lock

后，锁文件的

metadata.content-hash

会过期。通过运行以下命令重新生成：

bash

cd security_scanning && poetry lock --no-update && cd ..

此命令会刷新哈希值而不更改其他包版本。如果

poetry

可用，也可以在

security_scanning/

目录中使用

poetry add flashinfer-python@NEW_VERSION

自动更新

pyproject.toml

和

poetry.lock

（包括content-hash）。

Nightly / dev version special handling

夜间/开发版本特殊处理

If the user selects a nightly/dev version (e.g.,

0.7.0.dev20260401

The PyPI package may not exist — check first with

curl -s "https://pypi.org/pypi/flashinfer-python/VERSION/json"

If not on PyPI, the
```
security_scanning/poetry.lock
```
hashes cannot be updated. Warn the user and leave a
```
# TODO: update hashes when published to PyPI
```
comment.

The

requirements.txt

can pin to a git install instead:

flashinfer-python @ git+https://github.com/flashinfer-ai/flashinfer.git@TAG#egg=flashinfer-python

Ask the user which approach they prefer (PyPI pin vs git pin).

如果用户选择夜间/开发版本（例如

0.7.0.dev20260401

）：

PyPI上可能不存在该包——先通过

curl -s "https://pypi.org/pypi/flashinfer-python/VERSION/json"

检查。

如果不在PyPI上，则无法更新
```
security_scanning/poetry.lock
```
的哈希值。警告用户并留下
```
# TODO: 发布到PyPI后更新哈希值
```
注释。

requirements.txt

可以固定为git安装方式：

flashinfer-python @ git+https://github.com/flashinfer-ai/flashinfer.git@TAG#egg=flashinfer-python

询问用户偏好哪种方式（PyPI固定 vs git固定）。

Step 5: Verify Version Compatibility

步骤5：验证版本兼容性

After updating, check if any code has version-gated logic that needs adjusting:

bash

grep -rn 'flashinfer.*__version__\|flashinfer.*version' \
  tensorrt_llm/ --include="*.py"

Known locations with version checks:

tensorrt_llm/_torch/speculative/interface.py

—

flashinfer.__version__ >= "0.6.4"

If the new version is still >= the gated version, no changes needed. Otherwise, flag to the user.

更新完成后，检查是否有任何代码包含需要调整的版本门控逻辑：

bash

grep -rn 'flashinfer.*__version__\|flashinfer.*version' \
  tensorrt_llm/ --include="*.py"

已知存在版本检查的位置：

tensorrt_llm/_torch/speculative/interface.py

—

flashinfer.__version__ >= "0.6.4"

如果新版本仍大于等于门控版本，则无需更改。否则，向用户标记此问题。

Step 6: Summary

步骤6：总结

Print a summary of all changes made:

Old version → New version
Files modified (with line numbers)
Any warnings (e.g., poetry.lock hashes couldn't be updated for nightly)
Remind user to run
```
pip install -r requirements.txt
```
to test locally

Remind user to run relevant unit tests:

bash

pytest tests/unittest/_torch/flashinfer/ -v
pytest tests/unittest/_torch/attention/test_flashinfer_attention.py -v

打印所有已做更改的摘要：

旧版本 → 新版本
修改的文件（含行号）
任何警告（例如夜间版本无法更新poetry.lock哈希值）
提醒用户运行
```
pip install -r requirements.txt
```
进行本地测试

提醒用户运行相关单元测试：

bash

pytest tests/unittest/_torch/flashinfer/ -v
pytest tests/unittest/_torch/attention/test_flashinfer_attention.py -v

Step 7: Commit, Push, and Create PR

步骤7：提交、推送并创建PR

After all files are updated and verified:

If the user opted out of the
poetry.lock
update at Step 3 question 3, drop
security_scanning/poetry.lock
from the
git stash
,
git add
, and commit message in the snippets below.

所有文件更新并验证完成后：

如果用户在步骤3的问题3中选择不更新
poetry.lock
，则在以下代码片段的
git stash
、
git add
和提交消息中移除
security_scanning/poetry.lock
。

7a. Create a new branch from upstream main

7a：基于上游main创建新分支

bash

undefined

bash

undefined

Drop security_scanning/poetry.lock from this list if the user opted out.

如果用户选择不更新，从此列表中移除security_scanning/poetry.lock。

git stash push -m "flashinfer-upgrade-wip" -- requirements.txt security_scanning/pyproject.toml security_scanning/poetry.lock ATTRIBUTIONS-Python.md git checkout main git pull --rebase https://github.com/NVIDIA/TensorRT-LLM.git main git checkout -b ${GITHUB_USERNAME}/update_flashinfer_${NEW_VERSION} git stash pop


Where `GITHUB_USERNAME` comes from the fork remote (e.g., `yihwang-nv`) and
`NEW_VERSION` is the selected version (e.g., `0.6.7.post3`).


其中`GITHUB_USERNAME`来自fork远程仓库（例如`yihwang-nv`），`NEW_VERSION`是所选版本（例如`0.6.7.post3`）。

7b. Commit with DCO sign-off

7b：带DCO签署的提交

bash

undefined

bash

undefined

Drop security_scanning/poetry.lock from the

git add

list and the commit

如果用户选择不更新，从

git add

列表和提交正文中移除security_scanning/poetry.lock。

body if the user opted out.

—

git add requirements.txt security_scanning/pyproject.toml security_scanning/poetry.lock ATTRIBUTIONS-Python.md git commit -s -m "[None][chore] Update flashinfer-python from OLD to NEW

Bump flashinfer-python dependency to the latest stable release. Updated version pins in requirements.txt, security_scanning/pyproject.toml, security_scanning/poetry.lock (if updated), and ATTRIBUTIONS-Python.md."

undefined

git add requirements.txt security_scanning/pyproject.toml security_scanning/poetry.lock ATTRIBUTIONS-Python.md git commit -s -m "[None][chore] Update flashinfer-python from OLD to NEW

undefined

7c. Push the branch to the user's fork

7c：将分支推送到用户的fork

Identify the fork remote (from Step 0b — commonly named

fork

), then push:

bash

FORK_REMOTE=fork   # adjust if the user named their fork remote differently
BRANCH="${GITHUB_USERNAME}/update_flashinfer_${NEW_VERSION}"
git push -u "${FORK_REMOTE}" "${BRANCH}"

If the push is rejected for auth reasons, confirm

gh auth status

shows

repo

scope —

gh

installs a git credential helper that reuses its token for HTTPS pushes. Users on a non-default config dir must export

GH_CONFIG_DIR

in the same shell.

确定fork远程仓库（来自步骤0b——通常命名为

fork

），然后推送：

bash

FORK_REMOTE=fork   # 如果用户为fork远程仓库命名不同，请调整
BRANCH="${GITHUB_USERNAME}/update_flashinfer_${NEW_VERSION}"
git push -u "${FORK_REMOTE}" "${BRANCH}"

如果推送因认证原因被拒绝，确认

gh auth status

显示

repo

权限——

gh

会安装一个git凭证助手，将其令牌重用于HTTPS推送。使用非默认配置目录的用户必须在同一个shell中导出

GH_CONFIG_DIR

。

7d. Open the PR on

NVIDIA/TensorRT-LLM

7d：在

NVIDIA/TensorRT-LLM

上创建PR

bash

gh pr create \
  --repo NVIDIA/TensorRT-LLM \
  --base main \
  --head "${GITHUB_USERNAME}:${BRANCH}" \
  --title "[None][chore] Update flashinfer-python from ${OLD_VERSION} to ${NEW_VERSION}" \
  --body "$(cat <<EOF

bash

gh pr create \
  --repo NVIDIA/TensorRT-LLM \
  --base main \
  --head "${GITHUB_USERNAME}:${BRANCH}" \
  --title "[None][chore] Update flashinfer-python from ${OLD_VERSION} to ${NEW_VERSION}" \
  --body "$(cat <<EOF

Summary

Bump flashinfer-python from ${OLD_VERSION} to ${NEW_VERSION} (latest stable)
Updated version pins in requirements.txt, security_scanning/pyproject.toml, and ATTRIBUTIONS-Python.md (and security_scanning/poetry.lock if the user opted in)

Bump flashinfer-python from ${OLD_VERSION} to ${NEW_VERSION} (latest stable)
Updated version pins in requirements.txt, security_scanning/pyproject.toml, and ATTRIBUTIONS-Python.md (and security_scanning/poetry.lock if the user opted in)

Test plan

pip install -r requirements.txt installs successfully
pytest tests/unittest/_torch/flashinfer/ -v
pytest tests/unittest/_torch/attention/test_flashinfer_attention.py -v
CI pre-merge passes EOF )"


`gh pr create` prints the new PR URL on success. Report it back to the user.

pip install -r requirements.txt installs successfully
pytest tests/unittest/_torch/flashinfer/ -v
pytest tests/unittest/_torch/attention/test_flashinfer_attention.py -v
CI pre-merge passes EOF )"


`gh pr create`成功后会打印新PR的URL。将其反馈给用户。

Files Reference

文件参考

All files that contain flashinfer-python version pins:

File	Pattern
`requirements.txt`	`flashinfer-python==X.Y.Z`
`security_scanning/pyproject.toml`	`"flashinfer-python (==X.Y.Z)"`
`security_scanning/poetry.lock`	`name = "flashinfer-python"` block with version + hashes
`ATTRIBUTIONS-Python.md`	`## flashinfer-python (X.Y.Z)`

所有包含flashinfer-python版本固定的文件：

文件	匹配模式
`requirements.txt`	`flashinfer-python==X.Y.Z`
`security_scanning/pyproject.toml`	`"flashinfer-python (==X.Y.Z)"`
`security_scanning/poetry.lock`	`name = "flashinfer-python"` 块，包含版本和哈希值
`ATTRIBUTIONS-Python.md`	`## flashinfer-python (X.Y.Z)`

Notes

注意事项

The
```
setup.py
```
has a comment about git+https install URLs — no version pin to update there.
The
```
.pre-commit-config.yaml
```
and
```
pyproject.toml
```
reference flashinfer source files, not versions — no changes needed.
The
```
flashinfer/
```
submodule (if present) is separate from the
```
flashinfer-python
```
PyPI package.

```
setup.py
```
中有关于git+https安装URL的注释——此处无需更新版本固定。
```
.pre-commit-config.yaml
```
和
```
pyproject.toml
```
引用flashinfer源文件，而非版本——无需更改。
```
flashinfer/
```
子模块（如果存在）与
```
flashinfer-python
```
PyPI包是独立的。

trtllm-flashinfer-upgrade

Original

Translation

FlashInfer Version Upgrade Skill

FlashInfer版本升级技能

When to Use

使用场景

Prerequisites

前置条件

Step 0a: Determine GitHub Username

步骤0a：确定GitHub用户名

Step 0b: Verify Fork Remote

步骤0b：验证Fork远程仓库

Step 0c: Verify gh CLI Is Authenticated

步骤0c：验证gh CLI已认证

Workflow

工作流程

Step 1: Fetch Available Releases from GitHub

步骤1：从GitHub获取可用版本

Step 2: Check Current Version

步骤2：检查当前版本

Step 3: Ask User Preferences

步骤3：询问用户偏好

Step 4: Update All Version References

步骤4：更新所有版本引用

Updating security_scanning/poetry.lock hashes

更新security_scanning/poetry.lock哈希值

Nightly / dev version special handling

夜间/开发版本特殊处理

Step 5: Verify Version Compatibility

步骤5：验证版本兼容性

Step 6: Summary

步骤6：总结

Step 7: Commit, Push, and Create PR

步骤7：提交、推送并创建PR

7a. Create a new branch from upstream main

7a：基于上游main创建新分支

Drop security_scanning/poetry.lock from this list if the user opted out.

如果用户选择不更新，从此列表中移除security_scanning/poetry.lock。

7b. Commit with DCO sign-off

7b：带DCO签署的提交

Drop security_scanning/poetry.lock from the git add list and the commit

如果用户选择不更新，从git add列表和提交正文中移除security_scanning/poetry.lock。

body if the user opted out.

7c. Push the branch to the user's fork

7c：将分支推送到用户的fork

7d. Open the PR on NVIDIA/TensorRT-LLM

7d：在NVIDIA/TensorRT-LLM上创建PR

Summary

Summary

Test plan

Test plan

Files Reference

文件参考

Notes

注意事项

Step 0c: Verify
`gh`
CLI Is Authenticated

步骤0c：验证
`gh`
CLI已认证

Updating
`security_scanning/poetry.lock`
hashes

更新
`security_scanning/poetry.lock`
哈希值

Drop security_scanning/poetry.lock from the
`git add`
list and the commit

如果用户选择不更新，从
`git add`
列表和提交正文中移除security_scanning/poetry.lock。

7d. Open the PR on
`NVIDIA/TensorRT-LLM`

7d：在
`NVIDIA/TensorRT-LLM`
上创建PR