@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 1e3698393f
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 16, 00:45 UTC

[CI/Build] Add label automation for structured-output, speculative-decoding, v1 (#12280)

We have `v1`, `structured-output`, and `speculative-decoding` labels on github. This adds automation for applying these labels based on the files touched by a PR. Signed-off-by: Russell Bryant <rbryant@redhat.com> --------- Signed-off-by: Russell Bryant <rbryant@redhat.com>

Russell Bryant committed Feb 1, 2025 at 02:13 UTC 1e3698393fca22c70dc03539cf534181466d1d25
1 file changed +37
.github/mergify.yml
+37
@@ -35,6 +35,43 @@ pull_request_rules:
35 add:
36 - frontend
37
38 +- name: label-structured-output
39 + description: Automatically apply structured-output label
40 + conditions:
41 + - or:
42 + - files~=^vllm/model_executor/guided_decoding/
43 + - files=tests/model_executor/test_guided_processors.py
44 + - files=tests/entrypoints/llm/test_guided_generate.py
45 + - files=benchmarks/benchmark_serving_guided.py
46 + - files=benchmarks/benchmark_guided.py
47 + actions:
48 + label:
49 + add:
50 + - structured-output
51 +
52 +- name: label-speculative-decoding
53 + description: Automatically apply speculative-decoding label
54 + conditions:
55 + - or:
56 + - files~=^vllm/spec_decode/
57 + - files=vllm/model_executor/layers/spec_decode_base_sampler.py
58 + - files~=^tests/spec_decode/
59 + actions:
60 + label:
61 + add:
62 + - speculative-decoding
63 +
64 +- name: label-v1
65 + description: Automatically apply v1 label
66 + conditions:
67 + - or:
68 + - files~=^vllm/v1/
69 + - files~=^tests/v1/
70 + actions:
71 + label:
72 + add:
73 + - v1
74 +
75 - name: ping author on conflicts and add 'needs-rebase' label
76 conditions:
77 - conflict