mirror of
https://github.com/ROCm/ROCm.git
synced 2026-04-05 03:01:17 -04:00
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:
@@ -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
|
||||
|
||||
@@ -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
|
||||
|
||||
Reference in New Issue
Block a user