@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 15b86408a8
Fork 0

A high-throughput and memory-efficient inference and serving engine for LLMs

Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git

Synced Nov 17, 03:00 UTC

[Misc] add nccl in collect env (#4211)

youkaichao committed Apr 19, 2024 at 12:44 UTC 15b86408a89d5b998409e7fbe7850e937cc837da
5 files changed +6
.github/ISSUE_TEMPLATE/200-installation.yml
+1
@@ -18,6 +18,7 @@ body:
18 # For security purposes, please feel free to check the contents of collect_env.py before running it.
19 python collect_env.py
20 ```
21 + It is suggested to download and execute the latest script, as vllm might frequently update the diagnosis information needed for accurately and quickly responding to issues.
22 value: |
23 ```text
24 The output of `python collect_env.py`
.github/ISSUE_TEMPLATE/300-usage.yml
+1
@@ -18,6 +18,7 @@ body:
18 # For security purposes, please feel free to check the contents of collect_env.py before running it.
19 python collect_env.py
20 ```
21 + It is suggested to download and execute the latest script, as vllm might frequently update the diagnosis information needed for accurately and quickly responding to issues.
22 value: |
23 ```text
24 The output of `python collect_env.py`
.github/ISSUE_TEMPLATE/400-bug report.yml
+1
@@ -18,6 +18,7 @@ body:
18 # For security purposes, please feel free to check the contents of collect_env.py before running it.
19 python collect_env.py
20 ```
21 + It is suggested to download and execute the latest script, as vllm might frequently update the diagnosis information needed for accurately and quickly responding to issues.
22 value: |
23 ```text
24 The output of `python collect_env.py`
.github/ISSUE_TEMPLATE/700-performance discussion.yml
+1
@@ -39,6 +39,7 @@ body:
39 # For security purposes, please feel free to check the contents of collect_env.py before running it.
40 python collect_env.py
41 ```
42 + It is suggested to download and execute the latest script, as vllm might frequently update the diagnosis information needed for accurately and quickly responding to issues.
43 value: |
44 ```text
45 The output of `python collect_env.py`
collect_env.py
+2
@@ -63,6 +63,7 @@ DEFAULT_CONDA_PATTERNS = {
63 "magma",
64 "triton",
65 "optree",
66 + "nccl",
67 }
68
69 DEFAULT_PIP_PATTERNS = {
@@ -73,6 +74,7 @@ DEFAULT_PIP_PATTERNS = {
74 "triton",
75 "optree",
76 "onnx",
77 + "nccl",
78 }
79
80