@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 2131b597b1
Fork 0

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

[CI] Ping Mistral team for ministral/voxtral/mixtral/pixtral changes (#45153)

Signed-off-by: juliendenize <julien.denize@mistral.ai>

Julien Denize committed Jun 10, 2026 at 17:48 UTC 2131b597b18d051dced4c4a605d362fa37f46ed1
1 file changed +4 -4
.github/mergify.yml
+4 -4
@@ -144,12 +144,12 @@ pull_request_rules:
144 - label != stale
145 - or:
146 - files~=^examples/.*mistral.*\.py
147 - - files~=^tests/.*mistral.*\.py
148 - - files~=^vllm/model_executor/models/.*mistral.*\.py
147 + - files~=^tests/.*(?:mistral|voxtral|mixtral|pixtral).*\.py
148 + - files~=^vllm/model_executor/models/.*(?:mistral|voxtral|mixtral|pixtral).*\.py
149 - files~=^vllm/reasoning/.*mistral.*\.py
150 - files~=^vllm/tool_parsers/.*mistral.*\.py
151 - - files~=^vllm/transformers_utils/.*mistral.*\.py
152 - - title~=(?i)Mistral
151 + - files~=^vllm/transformers_utils/.*(?:mistral|voxtral|pixtral).*\.py
152 + - title~=(?i)(?:mistral|ministral|voxtral|mixtral|pixtral)
153 actions:
154 label:
155 add: