@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / d9cfbc891e
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, 15:45 UTC

[ci] Soft fail Entrypoints, Samplers, LoRA, Decoder-only VLM (#8872)

Signed-off-by: kevin <kevin@anyscale.com>

Kevin H. Luu committed Sep 26, 2024 at 15:02 UTC d9cfbc891e2e1d62d74c7aae93bde436a29bd574
1 file changed +4
.buildkite/test-pipeline.yaml
+4
@@ -83,6 +83,7 @@ steps:
83
84 - label: Entrypoints Test # 20min
85 working_dir: "/vllm-workspace/tests"
86 + soft_fail: true
87 fast_check: true
88 mirror_hardwares: [amd]
89 source_file_dependencies:
@@ -177,6 +178,7 @@ steps:
178 - pytest -v -s prefix_caching
179
180 - label: Samplers Test # 18min
181 + soft_fail: true
182 source_file_dependencies:
183 - vllm/model_executor/layers
184 - vllm/sampling_metadata.py
@@ -204,6 +206,7 @@ steps:
206
207 - label: LoRA Test %N # 30min each
208 mirror_hardwares: [amd]
209 + soft_fail: true
210 source_file_dependencies:
211 - vllm/lora
212 - tests/lora
@@ -308,6 +311,7 @@ steps:
311 - pytest -v -s models/decoder_only/language
312
313 - label: Decoder-only Multi-Modal Models Test # 56min
314 + soft_fail: true
315 #mirror_hardwares: [amd]
316 source_file_dependencies:
317 - vllm/