Skip to content

A4 & A4X TRTLLM GKE single-host inference benchmarking recipes #146

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
hmhv1222 merged 8 commits into from
Apr 21, 2026
Merged

A4 & A4X TRTLLM GKE single-host inference benchmarking recipes #146

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
e6445b7
A4 & A4X TRTLLM GKE Single-Host Inference Recipes, ReadMe and Config …
hmhv1222 Mar 13, 2026
65ccbf4
Add benchmarking configs warning paragraphs in TRTLLM inference ReadMe
hmhv1222 Mar 13, 2026
1c8a044
Remove memory resources constraint in A4X serving-launcher.yaml and c…
hmhv1222 Mar 13, 2026
16d4eab
Qwen3 235B A22B, Qwen 2.5 VL 7B & Llama 3.1 405B config files and lau…
hmhv1222 Mar 30, 2026
c5c2cb4
Support running VL models with trtllm-launcher.sh
hmhv1222 Mar 30, 2026
dc0a187
Add/modify A4 & A4X Qwen2.5-VL-7B, Qwen3-235B-A22B, Llama3.1-405B, TR…
hmhv1222 Apr 21, 2026
49822fd
Update model lists for TRTLLM inference on A4 & A4X in main ReadMe an…
hmhv1222 Apr 21, 2026
ab3c117
Use all 8 GPUs for A4 TRTLLM DeepSeek-R1 recipe; Adjust values.yaml
hmhv1222 Apr 21, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 22 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -82,6 +82,28 @@ Models | GPU Machine Type
| ---------------- | ---------------- | --------- | ------------------- | ------------ | ------------------ |
| **DeepSeek R1 671B** | [A4 (NVIDIA B200)](https://cloud.google.com/compute/docs/accelerator-optimized-machines#a4-vms) | vLLM | Inference | GKE | [Link](./inference/a4/single-host-serving/vllm/README.md)
| **DeepSeek R1 671B** | [A4 (NVIDIA B200)](https://cloud.google.com/compute/docs/accelerator-optimized-machines#a4-vms) | SGLang | Inference | GKE | [Link](./inference/a4/single-host-serving/sglang/README.md)
| **DeepSeek R1 671B** | [A4 (NVIDIA B200)](https://cloud.google.com/compute/docs/accelerator-optimized-machines#a4-vms) | TensorRT-LLM | Inference | GKE | [Link](./inference/a4/single-host-serving/tensorrt-llm/README.md)
| **Llama 3.1 405B** | [A4 (NVIDIA B200)](https://cloud.google.com/compute/docs/accelerator-optimized-machines#a4-vms) | TensorRT-LLM | Inference | GKE | [Link](./inference/a4/single-host-serving/tensorrt-llm/README.md)
| **Qwen 2.5 VL 7B** | [A4 (NVIDIA B200)](https://cloud.google.com/compute/docs/accelerator-optimized-machines#a4-vms) | TensorRT-LLM | Inference | GKE | [Link](./inference/a4/single-host-serving/tensorrt-llm/README.md)
| **Qwen 3 235B A22B** | [A4 (NVIDIA B200)](https://cloud.google.com/compute/docs/accelerator-optimized-machines#a4-vms) | TensorRT-LLM | Inference | GKE | [Link](./inference/a4/single-host-serving/tensorrt-llm/README.md)
| **Qwen 3 32B** | [A4 (NVIDIA B200)](https://cloud.google.com/compute/docs/accelerator-optimized-machines#a4-vms) | TensorRT-LLM | Inference | GKE | [Link](./inference/a4/single-host-serving/tensorrt-llm/README.md)

### Inference benchmarks A4X

| Models | GPU Machine Type | Framework | Workload Type | Orchestrator | Link to the recipe |
| ---------------- | ---------------- | --------- | ------------------- | ------------ | ------------------ |
| **DeepSeek R1 671B** | [A4X (NVIDIA GB200)](https://cloud.google.com/compute/docs/accelerator-optimized-machines#a4x-vms) | vLLM | Inference | GKE | [Link](./inference/a4x/single-host-serving/vllm/README.md)
| **Wan2.2 T2V A14B Diffusers** | [A4X (NVIDIA GB200)](https://cloud.google.com/compute/docs/accelerator-optimized-machines#a4x-vms) | SGLang | Inference | GKE | [Link](./inference/a4x/single-host-serving/sglang/README.md)
| **Wan2.2 I2V A14B Diffusers** | [A4X (NVIDIA GB200)](https://cloud.google.com/compute/docs/accelerator-optimized-machines#a4x-vms) | SGLang | Inference | GKE | [Link](./inference/a4x/single-host-serving/sglang/README.md)
| **DeepSeek R1 671B** | [A4X (NVIDIA GB200)](https://cloud.google.com/compute/docs/accelerator-optimized-machines#a4x-vms) | TensorRT-LLM | Inference | GKE | [Link](./inference/a4x/single-host-serving/tensorrt-llm/README.md) <br> <br> [Link for Using Google Cloud Storage (GCS) as Storage Option]((./inference/a4x/single-host-serving/tensorrt-llm-gcs/README.md)) <br> <br> [Link for Using Lustre as Storage Option]((./inference/a4x/single-host-serving/tensorrt-llm-lustre/README.md))
| **Llama 3.1 405B** | [A4X (NVIDIA GB200)](https://cloud.google.com/compute/docs/accelerator-optimized-machines#a4x-vms) | TensorRT-LLM | Inference | GKE | [Link](./inference/a4x/single-host-serving/tensorrt-llm/README.md)
| **Llama 3.1 70B** | [A4X (NVIDIA GB200)](https://cloud.google.com/compute/docs/accelerator-optimized-machines#a4x-vms) | TensorRT-LLM | Inference | GKE | [Link](./inference/a4x/single-host-serving/tensorrt-llm/README.md)
| **Llama 3.1 8B** | [A4X (NVIDIA GB200)](https://cloud.google.com/compute/docs/accelerator-optimized-machines#a4x-vms) | TensorRT-LLM | Inference | GKE | [Link](./inference/a4x/single-host-serving/tensorrt-llm/README.md)
| **Qwen 2.5 VL 7B** | [A4X (NVIDIA GB200)](https://cloud.google.com/compute/docs/accelerator-optimized-machines#a4x-vms) | TensorRT-LLM | Inference | GKE | [Link](./inference/a4x/single-host-serving/tensorrt-llm/README.md)
| **Qwen 3 235B A22B** | [A4X (NVIDIA GB200)](https://cloud.google.com/compute/docs/accelerator-optimized-machines#a4x-vms) | TensorRT-LLM | Inference | GKE | [Link](./inference/a4x/single-host-serving/tensorrt-llm/README.md)
| **Qwen 3 32B** | [A4X (NVIDIA GB200)](https://cloud.google.com/compute/docs/accelerator-optimized-machines#a4x-vms) | TensorRT-LLM | Inference | GKE | [Link](./inference/a4x/single-host-serving/tensorrt-llm/README.md)
| **Qwen 3 4B** | [A4X (NVIDIA GB200)](https://cloud.google.com/compute/docs/accelerator-optimized-machines#a4x-vms) | TensorRT-LLM | Inference | GKE | [Link](./inference/a4x/single-host-serving/tensorrt-llm/README.md)


### Inference benchmarks G4

Expand Down
Loading