Add latest rocm/vllm Docker details in vLLM inference benchmark guide (#4824)

* update rocm/vllm Docker details to latest release

* Add previous vLLM version

* fix 'further reading' xrefs

* improve model grouping names

* fix links

* update model picker text
This commit is contained in:
Peter Park
2025-05-28 14:20:18 -04:00
committed by GitHub
parent 0acb457389
commit cebf0f5975
4 changed files with 42 additions and 24 deletions

View File

@@ -1,14 +1,14 @@
vllm_benchmark:
unified_docker:
latest:
pull_tag: rocm/vllm:rocm6.3.1_instinct_vllm0.8.3_20250415
docker_hub_url: https://hub.docker.com/layers/rocm/vllm/rocm6.3.1_instinct_vllm0.8.3_20250415/images/sha256-ad9062dea3483d59dedb17c67f7c49f30eebd6eb37c3fac0a171fb19696cc845
pull_tag: rocm/vllm:rocm6.3.1_vllm0.8.3_20250415
docker_hub_url: https://hub.docker.com/layers/rocm/vllm/rocm6.3.1_vllm_0.8.5_20250513/images/sha256-5c8b4436dd0464119d9df2b44c745fadf81512f18ffb2f4b5dc235c71ebe26b4
rocm_version: 6.3.1
vllm_version: 0.8.3
pytorch_version: 2.7.0 (dev nightly)
hipblaslt_version: 0.13
vllm_version: 0.8.5
pytorch_version: 2.7.0+gitf717b2a
hipblaslt_version: 0.15
model_groups:
- group: Llama
- group: Meta Llama
tag: llama
models:
- model: Llama 3.1 8B
@@ -56,7 +56,7 @@ vllm_benchmark:
model_repo: amd/Llama-3.1-405B-Instruct-FP8-KV
url: https://huggingface.co/amd/Llama-3.1-405B-Instruct-FP8-KV
precision: float8
- group: Mistral
- group: Mistral AI
tag: mistral
models:
- model: Mixtral MoE 8x7B
@@ -108,7 +108,7 @@ vllm_benchmark:
url: https://huggingface.co/Qwen/QwQ-32B
precision: float16
tunableop: true
- group: DBRX
- group: Databricks DBRX
tag: dbrx
models:
- model: DBRX Instruct
@@ -121,7 +121,7 @@ vllm_benchmark:
model_repo: amd/dbrx-instruct-FP8-KV
url: https://huggingface.co/amd/dbrx-instruct-FP8-KV
precision: float8
- group: Gemma
- group: Google Gemma
tag: gemma
models:
- model: Gemma 2 27B

View File

@@ -1,6 +1,6 @@
megatron-lm_benchmark:
model_groups:
- group: Llama
- group: Meta Llama
tag: llama
models:
- model: Llama 3.3 70B
@@ -20,7 +20,7 @@ megatron-lm_benchmark:
mad_tag: pyt_megatron_lm_train_deepseek-v3-proxy
- model: DeepSeek-V2-Lite
mad_tag: pyt_megatron_lm_train_deepseek-v2-lite-16b
- group: Mistral
- group: Mistral AI
tag: mistral
models:
- model: Mixtral 8x7B