Skip to content
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.

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

[Minor] Updating Dev Docker docs #331

Open
wants to merge 5 commits into
base: main
Choose a base branch
from
Open
Changes from 2 commits
Commits
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
17 changes: 8 additions & 9 deletions docs/dev-docker/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -24,12 +24,12 @@ The performance data below was measured on a server with MI300X accelerators wit
|---|---|
| BKC | 24.13 |
| ROCm | version ROCm 6.3 |
| amdgpu | build 2009461 |
| amdgpu | build 2041575 |
| OS | Ubuntu 22.04 |
| Linux Kernel | 5.15.0-117-generic |
| BMCVersion | C2789.BC.0809.00 |
| BiosVersion | C2789.5.BS.1C11.AG.1 |
| CpldVersion | 02.02.00 |
| Linux Kernel | 5.15.0-70-generic |
| BMCVersion | C2789.BC.0811.00 |
| BiosVersion | C2789.5.BS.1C17.GN.1 |
| CpldVersion | 02.03.00 |
| DCSCMCpldVersion | 02.02.00 |
| CX7 | FW 28.40.1000 |
| RAM | 1 TB |
Expand Down Expand Up @@ -261,7 +261,8 @@ Benchmark Meta-Llama-3.1-405B FP8 with input 128 tokens, output 128 tokens and t
--num-scheduler-steps 10 \
--tensor-parallel-size 8 \
--input-len 128 \
--output-len 128
--output-len 128 \
--enable-chunked-prefill false
arakowsk-amd marked this conversation as resolved.
Show resolved Hide resolved

If you want to run Meta-Llama-3.1-405B FP16, please run

Expand All @@ -278,9 +279,7 @@ If you want to run Meta-Llama-3.1-405B FP16, please run
--swap-space 16 \
--max-model-len 8192 \
--max-num-batched-tokens 65536 \
--swap-space
--max-model-len
--gpu-memory-utilization 0.99
--enable-chunked-prefill false

For fp8 quantized Llama3.18B/70B models:

Expand Down
Loading