ROCm
diff --git a/‎.buildkite/check-wheel-size.py
Lines changed: 4 additions & 2 deletions b/‎.buildkite/check-wheel-size.py
Lines changed: 4 additions & 2 deletions
diff --git a/‎.buildkite/generate_index.py
Lines changed: 2 additions & 0 deletions b/‎.buildkite/generate_index.py
Lines changed: 2 additions & 0 deletions
diff --git a/‎.buildkite/lm-eval-harness/configs/SparseLlama3.1_2of4_fp8_compressed.yaml
Lines changed: 11 additions & 0 deletions b/‎.buildkite/lm-eval-harness/configs/SparseLlama3.1_2of4_fp8_compressed.yaml
Lines changed: 11 additions & 0 deletions
diff --git a/‎.buildkite/lm-eval-harness/test_lm_eval_correctness.py
Lines changed: 1 addition & 0 deletions b/‎.buildkite/lm-eval-harness/test_lm_eval_correctness.py
Lines changed: 1 addition & 0 deletions
diff --git a/‎.buildkite/nightly-benchmarks/README.md
Lines changed: 18 additions & 28 deletions b/‎.buildkite/nightly-benchmarks/README.md
Lines changed: 18 additions & 28 deletions
diff --git a/‎.buildkite/nightly-benchmarks/benchmark-pipeline.yaml
Lines changed: 6 additions & 0 deletions b/‎.buildkite/nightly-benchmarks/benchmark-pipeline.yaml
Lines changed: 6 additions & 0 deletions
diff --git a/‎.buildkite/nightly-benchmarks/nightly-annotation.md
Lines changed: 10 additions & 11 deletions b/‎.buildkite/nightly-benchmarks/nightly-annotation.md
Lines changed: 10 additions & 11 deletions
diff --git a/‎.buildkite/nightly-benchmarks/nightly-descriptions.md
Lines changed: 3 additions & 3 deletions b/‎.buildkite/nightly-benchmarks/nightly-descriptions.md
Lines changed: 3 additions & 3 deletions
diff --git a/‎.buildkite/nightly-benchmarks/performance-benchmarks-descriptions.md
Lines changed: 2 additions & 8 deletions b/‎.buildkite/nightly-benchmarks/performance-benchmarks-descriptions.md
Lines changed: 2 additions & 8 deletions
diff --git a/‎.buildkite/nightly-benchmarks/scripts/convert-results-json-to-markdown.py
Lines changed: 2 additions & 0 deletions b/‎.buildkite/nightly-benchmarks/scripts/convert-results-json-to-markdown.py
Lines changed: 2 additions & 0 deletions
diff --git a/‎.buildkite/nightly-benchmarks/scripts/download-tokenizer.py
Lines changed: 2 additions & 0 deletions b/‎.buildkite/nightly-benchmarks/scripts/download-tokenizer.py
Lines changed: 2 additions & 0 deletions
diff --git a/‎.buildkite/nightly-benchmarks/scripts/generate-nightly-markdown.py
Lines changed: 2 additions & 0 deletions b/‎.buildkite/nightly-benchmarks/scripts/generate-nightly-markdown.py
Lines changed: 2 additions & 0 deletions
diff --git a/‎.buildkite/nightly-benchmarks/scripts/get-lmdeploy-modelname.py
Lines changed: 2 additions & 0 deletions b/‎.buildkite/nightly-benchmarks/scripts/get-lmdeploy-modelname.py
Lines changed: 2 additions & 0 deletions
diff --git a/‎.buildkite/nightly-benchmarks/scripts/run-performance-benchmarks.sh
Lines changed: 5 additions & 0 deletions b/‎.buildkite/nightly-benchmarks/scripts/run-performance-benchmarks.sh
Lines changed: 5 additions & 0 deletions
diff --git a/‎.buildkite/nightly-benchmarks/scripts/summary-nightly-results.py
Lines changed: 2 additions & 0 deletions b/‎.buildkite/nightly-benchmarks/scripts/summary-nightly-results.py
Lines changed: 2 additions & 0 deletions
diff --git a/‎.buildkite/nightly-benchmarks/tests/latency-tests.json
Lines changed: 1 addition & 1 deletion b/‎.buildkite/nightly-benchmarks/tests/latency-tests.json
Lines changed: 1 addition & 1 deletion
diff --git a/‎.buildkite/release-pipeline.yaml
Lines changed: 7 additions & 2 deletions b/‎.buildkite/release-pipeline.yaml
Lines changed: 7 additions & 2 deletions
diff --git a/‎.buildkite/run-gh200-test.sh
Lines changed: 2 additions & 2 deletions b/‎.buildkite/run-gh200-test.sh
Lines changed: 2 additions & 2 deletions
diff --git a/‎.buildkite/run-neuron-test.sh
Lines changed: 1 addition & 4 deletions b/‎.buildkite/run-neuron-test.sh
Lines changed: 1 addition & 4 deletions
diff --git a/‎.buildkite/run-tpu-test.sh
100644100755 b/‎.buildkite/run-tpu-test.sh
100644100755
@@ -1,12 +1,14 @@
+# SPDX-License-Identifier: Apache-2.0
+
 import os
 import sys
 import zipfile
 
-# Read the VLLM_MAX_SIZE_MB environment variable, defaulting to 300 MiB
+# Read the VLLM_MAX_SIZE_MB environment variable, defaulting to 400 MiB
 # Note that we have 400 MiB quota, please use it wisely.
 # See https://github.com/pypi/support/issues/3792 .
 # Please also sync the value with the one in Dockerfile.
-VLLM_MAX_SIZE_MB = int(os.environ.get('VLLM_MAX_SIZE_MB', 300))
+VLLM_MAX_SIZE_MB = int(os.environ.get('VLLM_MAX_SIZE_MB', 400))
 
 
 def print_top_10_largest_files(zip_file):
 
@@ -1,3 +1,5 @@
+# SPDX-License-Identifier: Apache-2.0
+
 import argparse
 import os
 
 
@@ -0,0 +1,11 @@
+# bash ./run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/SparseLlama-3.1-8B-gsm8k-pruned.2of4-chnl_wts_per_tok_dyn_act_fp8-BitM -b "auto" -t 2
+model_name: "nm-testing/SparseLlama-3.1-8B-gsm8k-pruned.2of4-chnl_wts_per_tok_dyn_act_fp8-BitM"
+tasks:
+- name: "gsm8k"
+  metrics:
+  - name: "exact_match,strict-match"
+    value: 0.6353
+  - name: "exact_match,flexible-extract"
+    value: 0.637
+limit: null
+num_fewshot: null 
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: Apache-2.0
 """
 LM eval harness on model to compare vs HF baseline computed offline.
 Configs are found in configs/$MODEL.yaml
 
@@ -1,15 +1,13 @@
 # vLLM benchmark suite
 
-
 ## Introduction
 
 This directory contains two sets of benchmark for vllm.
+
 - Performance benchmark: benchmark vllm's performance under various workload, for **developers** to gain clarity on whether their PR improves/degrades vllm's performance
 - Nightly benchmark: compare vllm's performance against alternatives (tgi, trt-llm and lmdeploy), for **the public** to know when to choose vllm.
 
-
-See  [vLLM performance dashboard](https://perf.vllm.ai) for the latest performance benchmark results and [vLLM GitHub README](https://github.com/vllm-project/vllm/blob/main/README.md) for latest nightly benchmark results.
-
+See [vLLM performance dashboard](https://perf.vllm.ai) for the latest performance benchmark results and [vLLM GitHub README](https://github.com/vllm-project/vllm/blob/main/README.md) for latest nightly benchmark results.
 
 ## Performance benchmark quick overview
 
@@ -19,17 +17,14 @@ See  [vLLM performance dashboard](https://perf.vllm.ai) for the latest performan
 
 **For benchmarking developers**: please try your best to constraint the duration of benchmarking to about 1 hr so that it won't take forever to run.
 
-
 ## Nightly benchmark quick overview
 
-**Benchmarking Coverage**: Fix-qps serving on A100 (the support for FP8 benchmark on H100 is coming!) on Llama-3 8B, 70B and Mixtral 8x7B. 
+**Benchmarking Coverage**: Fix-qps serving on A100 (the support for FP8 benchmark on H100 is coming!) on Llama-3 8B, 70B and Mixtral 8x7B.
 
 **Benchmarking engines**: vllm, TGI, trt-llm and lmdeploy.
 
 **Benchmarking Duration**: about 3.5hrs.
 
-
-
 ## Trigger the benchmark
 
 Performance benchmark will be triggered when:
@@ -39,16 +34,11 @@ Performance benchmark will be triggered when:
 Nightly benchmark will be triggered when:
 - Every commit for those PRs with `perf-benchmarks` label and `nightly-benchmarks` label.
 
-
-
-
 ## Performance benchmark details
 
-
 See [performance-benchmarks-descriptions.md](performance-benchmarks-descriptions.md) for detailed descriptions, and use `tests/latency-tests.json`, `tests/throughput-tests.json`, `tests/serving-tests.json` to configure the test cases.
 
-
-#### Latency test
+### Latency test
 
 Here is an example of one test inside `latency-tests.json`:
 
@@ -68,23 +58,25 @@ Here is an example of one test inside `latency-tests.json`:
 ```
 
 In this example:
--  The `test_name` attributes is a unique identifier for the test. In `latency-tests.json`, it must start with `latency_`.
--  The `parameters` attribute control the command line arguments to be used for `benchmark_latency.py`. Note that please use underline `_` instead of the dash `-` when specifying the command line arguments, and `run-performance-benchmarks.sh` will convert the underline to dash when feeding the arguments to `benchmark_latency.py`. For example, the corresponding command line arguments for `benchmark_latency.py` will be `--model meta-llama/Meta-Llama-3-8B --tensor-parallel-size 1 --load-format dummy --num-iters-warmup 5 --num-iters 15`
+
+- The `test_name` attributes is a unique identifier for the test. In `latency-tests.json`, it must start with `latency_`.
+- The `parameters` attribute control the command line arguments to be used for `benchmark_latency.py`. Note that please use underline `_` instead of the dash `-` when specifying the command line arguments, and `run-performance-benchmarks.sh` will convert the underline to dash when feeding the arguments to `benchmark_latency.py`. For example, the corresponding command line arguments for `benchmark_latency.py` will be `--model meta-llama/Meta-Llama-3-8B --tensor-parallel-size 1 --load-format dummy --num-iters-warmup 5 --num-iters 15`
 
 Note that the performance numbers are highly sensitive to the value of the parameters. Please make sure the parameters are set correctly.
 
 WARNING: The benchmarking script will save json results by itself, so please do not configure `--output-json` parameter in the json file.
 
+### Throughput test
 
-#### Throughput test
 The tests are specified in `throughput-tests.json`. The syntax is similar to `latency-tests.json`, except for that the parameters will be fed forward to `benchmark_throughput.py`.
 
 The number of this test is also stable -- a slight change on the value of this number might vary the performance numbers by a lot.
 
-#### Serving test
+### Serving test
+
 We test the throughput by using `benchmark_serving.py` with request rate = inf to cover the online serving overhead. The corresponding parameters are in `serving-tests.json`, and here is an example:
 
-```
+```json
 [
     {
         "test_name": "serving_llama8B_tp1_sharegpt",
@@ -109,6 +101,7 @@ We test the throughput by using `benchmark_serving.py` with request rate = inf t
 ```
 
 Inside this example:
+
 - The `test_name` attribute is also a unique identifier for the test. It must start with `serving_`.
 - The `server-parameters` includes the command line arguments for vLLM server.
 - The `client-parameters` includes the command line arguments for `benchmark_serving.py`.
@@ -118,36 +111,33 @@ The number of this test is less stable compared to the delay and latency benchma
 
 WARNING: The benchmarking script will save json results by itself, so please do not configure `--save-results` or other results-saving-related parameters in `serving-tests.json`.
 
-#### Visualizing the results
+### Visualizing the results
+
 The `convert-results-json-to-markdown.py` helps you put the benchmarking results inside a markdown table, by formatting [descriptions.md](tests/descriptions.md) with real benchmarking results.
 You can find the result presented as a table inside the `buildkite/performance-benchmark` job page.
 If you do not see the table, please wait till the benchmark finish running.
 The json version of the table (together with the json version of the benchmark) will be also attached to the markdown file.
 The raw benchmarking results (in the format of json files) are in the `Artifacts` tab of the benchmarking.
 
-
-
 ## Nightly test details
 
 See [nightly-descriptions.md](nightly-descriptions.md) for the detailed description on test workload, models and docker containers of benchmarking other llm engines.
 
+### Workflow
 
-#### Workflow
-
-- The [nightly-pipeline.yaml](nightly-pipeline.yaml) specifies the docker containers for different LLM serving engines. 
+- The [nightly-pipeline.yaml](nightly-pipeline.yaml) specifies the docker containers for different LLM serving engines.
 - Inside each container, we run [run-nightly-suite.sh](run-nightly-suite.sh), which will probe the serving engine of the current container.
 - The `run-nightly-suite.sh` will redirect the request to `tests/run-[llm serving engine name]-nightly.sh`, which parses the workload described in [nightly-tests.json](tests/nightly-tests.json) and performs the benchmark.
 - At last, we run [scripts/plot-nightly-results.py](scripts/plot-nightly-results.py) to collect and plot the final benchmarking results, and update the results to buildkite.
 
-#### Nightly tests
+### Nightly tests
 
 In [nightly-tests.json](tests/nightly-tests.json), we include the command line arguments for benchmarking commands, together with the benchmarking test cases. The format is highly similar to performance benchmark.
 
-#### Docker containers
+### Docker containers
 
 The docker containers for benchmarking are specified in `nightly-pipeline.yaml`.
 
 WARNING: the docker versions are HARD-CODED and SHOULD BE ALIGNED WITH `nightly-descriptions.md`. The docker versions need to be hard-coded as there are several version-specific bug fixes inside `tests/run-[llm serving engine name]-nightly.sh`.
 
 WARNING: populating `trt-llm` to latest version is not easy, as it requires updating several protobuf files in [tensorrt-demo](https://github.com/neuralmagic/tensorrt-demo.git).
-
@@ -70,6 +70,12 @@ steps:
     #key: block-h100
     #depends_on: ~
 
+  - label: "Cleanup H100"
+    agents:
+      queue: H100
+    depends_on: ~
+    command: docker system prune -a --volumes --force
+
   - label: "H100"
     # skip: "use this flag to conditionally skip the benchmark step, useful for PR testing"
     agents:
 
@@ -9,20 +9,19 @@ This file contains the downloading link for benchmarking results.
 
 Please download the visualization scripts in the post
 
-
 ## Results reproduction
 
 - Find the docker we use in `benchmarking pipeline`
 - Deploy the docker, and inside the docker:
-  - Download `nightly-benchmarks.zip`. 
-  - In the same folder, run the following code
-```
-export HF_TOKEN=<your HF token>
-apt update
-apt install -y git
-unzip nightly-benchmarks.zip
-VLLM_SOURCE_CODE_LOC=./ bash .buildkite/nightly-benchmarks/scripts/run-nightly-benchmarks.sh
-```
+  - Download `nightly-benchmarks.zip`.
+  - In the same folder, run the following code:
 
-And the results will be inside `./benchmarks/results`.
+  ```console
+  export HF_TOKEN=<your HF token>
+  apt update
+  apt install -y git
+  unzip nightly-benchmarks.zip
+  VLLM_SOURCE_CODE_LOC=./ bash .buildkite/nightly-benchmarks/scripts/run-nightly-benchmarks.sh
+  ```
 
+And the results will be inside `./benchmarks/results`.
@@ -2,14 +2,14 @@
 # Nightly benchmark
 
 This benchmark aims to:
+
 - Provide performance clarity: Provide clarity on which one (vllm, tensorrt-llm, lmdeploy and SGLang) leads in performance in what workload.
 - Be reproducible: one can run the exact same set of benchmarking commands inside the exact same docker by following reproducing instructions.
 
 Latest results: [results link](https://blog.vllm.ai/2024/09/05/perf-update.html), scroll to the end.
 
 Latest reproduction guilde: [github issue link](https://github.com/vllm-project/vllm/issues/8176)
 
-
 ## Setup
 
 - Docker images:
@@ -33,7 +33,7 @@ Latest reproduction guilde: [github issue link](https://github.com/vllm-project/
     - Queries are randomly sampled, and arrival patterns are determined via Poisson process, but all with fixed random seed.
   - Evaluation metrics: Throughput (higher the better), TTFT (time to the first token, lower the better), ITL (inter-token latency, lower the better).
 
-# Known issues
+## Known issues
 
 - TRT-LLM crashes with Llama 3.1 8B [issue](https://github.com/NVIDIA/TensorRT-LLM/issues/2105).
-- TGI does not support `ignore-eos` flag.
+- TGI does not support `ignore-eos` flag.
@@ -7,10 +7,8 @@
 - Models: llama-3.1 8B, llama-3 70B, mixtral 8x7B.
 - Evaluation metrics: end-to-end latency (mean, median, p99).
 
-
 {latency_tests_markdown_table}
 
-
 ## Throughput tests
 
 - Input length: randomly sample 200 prompts from ShareGPT dataset (with fixed random seed).
@@ -19,10 +17,8 @@
 - Models: llama-3.1 8B, llama-3 70B, mixtral 8x7B.
 - Evaluation metrics: throughput.
 
-
 {throughput_tests_markdown_table}
 
-
 ## Serving tests
 
 - Input length: randomly sample 200 prompts from ShareGPT dataset (with fixed random seed).
@@ -33,13 +29,11 @@
 - We also added a speculative decoding test for llama-3 70B, under QPS 2
 - Evaluation metrics: throughput, TTFT (time to the first token, with mean, median and p99), ITL (inter-token latency, with mean, median and p99).
 
-
 {serving_tests_markdown_table}
 
-
 ## json version of the benchmarking tables
 
-This section contains the data of the markdown tables above in JSON format. 
+This section contains the data of the markdown tables above in JSON format.
 You can load the benchmarking tables into pandas dataframes as follows:
 
 ```python
@@ -54,9 +48,9 @@ serving_results = pd.DataFrame.from_dict(benchmarking_results["serving"])
 ```
 
 The json string for all benchmarking tables:
+
 ```json
 {benchmarking_results_in_json_string}
 ```
 
 You can also check the raw experiment data in the Artifact tab of the Buildkite page.
-
@@ -1,3 +1,5 @@
+# SPDX-License-Identifier: Apache-2.0
+
 import json
 import os
 from pathlib import Path
 
@@ -1,3 +1,5 @@
+# SPDX-License-Identifier: Apache-2.0
+
 import argparse
 
 from transformers import AutoTokenizer
 
@@ -1,3 +1,5 @@
+# SPDX-License-Identifier: Apache-2.0
+
 import argparse
 import json
 from pathlib import Path
 
@@ -1,3 +1,5 @@
+# SPDX-License-Identifier: Apache-2.0
+
 from lmdeploy.serve.openai.api_client import APIClient
 
 api_client = APIClient("http://localhost:8000")
 
@@ -345,6 +345,11 @@ main() {
   check_gpus
   check_hf_token
 
+  # Set to v1 to run v1 benchmark
+  if [[ "${ENGINE_VERSION:-v0}" == "v1" ]]; then
+    export VLLM_USE_V1=1
+  fi
+
   # dependencies
   (which wget && which curl) || (apt-get update && apt-get install -y wget curl)
   (which jq) || (apt-get update && apt-get -y install jq)
 
@@ -1,3 +1,5 @@
+# SPDX-License-Identifier: Apache-2.0
+
 import datetime
 import json
 import os
 
@@ -29,4 +29,4 @@
             "num-iters": 15
         }
     }
-]
+]
@@ -56,6 +56,11 @@ steps:
     env:
       DOCKER_BUILDKIT: "1"
 
+  - input: "Provide Release version here"
+    fields:
+      - text: "What is the release version?"
+        key: "release-version"
+
   - block: "Build CPU release image"
     key: block-cpu-release-image-build
     depends_on: ~
@@ -66,7 +71,7 @@ steps:
       queue: cpu_queue_postmerge
     commands:
       - "aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin public.ecr.aws/q9t5s3a7"
-      - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg GIT_REPO_CHECK=1 --tag public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:$RELEASE_VERSION --progress plain -f Dockerfile.cpu ."
-      - "docker push public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:$RELEASE_VERSION"
+      - "DOCKER_BUILDKIT=1 docker build --build-arg max_jobs=16 --build-arg GIT_REPO_CHECK=1 --tag public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:$(buildkite-agent meta-data get release-version) --progress plain -f Dockerfile.cpu ."
+      - "docker push public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:$(buildkite-agent meta-data get release-version)"
     env:
       DOCKER_BUILDKIT: "1"
@@ -23,6 +23,6 @@ trap remove_docker_container EXIT
 remove_docker_container
 
 # Run the image and test offline inference
-docker run --name gh200-test --gpus=all --entrypoint="" gh200-test bash -c '
-    python3 examples/offline_inference/basic.py
+docker run -e HF_TOKEN -v /root/.cache/huggingface:/root/.cache/huggingface --name gh200-test --gpus=all --entrypoint="" gh200-test bash -c '
+    python3 examples/offline_inference/cli.py --model meta-llama/Llama-3.2-1B
 '
@@ -29,9 +29,6 @@ if [ -f /tmp/neuron-docker-build-timestamp ]; then
         docker image prune -f
         # Remove unused volumes / force the system prune for old images as well.
         docker volume prune -f && docker system prune -f
-        # Remove huggingface model artifacts and compiler cache
-        rm -rf "${HF_MOUNT:?}/*"
-        rm -rf "${NEURON_COMPILE_CACHE_MOUNT:?}/*"
         echo "$current_time" > /tmp/neuron-docker-build-timestamp
     fi
 else
@@ -54,4 +51,4 @@ docker run --rm -it --device=/dev/neuron0 --device=/dev/neuron1 --network host \
        -e "NEURON_COMPILE_CACHE_URL=${NEURON_COMPILE_CACHE_MOUNT}" \
        --name "${container_name}" \
        ${image_name} \
-       /bin/bash -c "python3 /workspace/vllm/examples/offline_inference/neuron.py"
+       /bin/bash -c "python3 /workspace/vllm/examples/offline_inference/neuron.py && python3 -m pytest /workspace/vllm/tests/neuron/ -v --capture=tee-sys"
Original file line number	Diff line number	Diff line change
`@@ -1,3 +1,5 @@`
	`1`	`+# SPDX-License-Identifier: Apache-2.0`
	`2`	`+`
`1`	`3`	`import argparse`
`2`	`4`	`import os`
`3`	`5`
Original file line number	Diff line number	Diff line change
`@@ -1,3 +1,4 @@`
	`1`	`+# SPDX-License-Identifier: Apache-2.0`
`1`	`2`	`"""`
`2`	`3`	`LM eval harness on model to compare vs HF baseline computed offline.`
`3`	`4`	`Configs are found in configs/$MODEL.yaml`
Original file line number	Diff line number	Diff line change
`@@ -1,3 +1,5 @@`
	`1`	`+# SPDX-License-Identifier: Apache-2.0`
	`2`	`+`
`1`	`3`	`import json`
`2`	`4`	`import os`
`3`	`5`	`from pathlib import Path`
Original file line number	Diff line number	Diff line change
`@@ -1,3 +1,5 @@`
	`1`	`+# SPDX-License-Identifier: Apache-2.0`
	`2`	`+`
`1`	`3`	`from lmdeploy.serve.openai.api_client import APIClient`
`2`	`4`
`3`	`5`	`api_client = APIClient("http://localhost:8000")`
Original file line number	Diff line number	Diff line change
`@@ -1,3 +1,5 @@`
	`1`	`+# SPDX-License-Identifier: Apache-2.0`
	`2`	`+`
`1`	`3`	`import datetime`
`2`	`4`	`import json`
`3`	`5`	`import os`
Original file line number	Diff line number	Diff line change
`@@ -29,4 +29,4 @@`
`29`	`29`	`"num-iters": 15`
`30`	`30`	`}`
`31`	`31`	`}`
`32`		`-]`
	`32`	`+]`
Original file line number	Diff line number	Diff line change
`@@ -23,6 +23,6 @@ trap remove_docker_container EXIT`
`23`	`23`	`remove_docker_container`
`24`	`24`
`25`	`25`	`# Run the image and test offline inference`
`26`		`-docker run --name gh200-test --gpus=all --entrypoint="" gh200-test bash -c '`
`27`		`- python3 examples/offline_inference/basic.py`
	`26`	`+docker run -e HF_TOKEN -v /root/.cache/huggingface:/root/.cache/huggingface --name gh200-test --gpus=all --entrypoint="" gh200-test bash -c '`
	`27`	`+ python3 examples/offline_inference/cli.py --model meta-llama/Llama-3.2-1B`
`28`	`28`	`'`