Optimize Kimi-K2.5-FP4 on AMD MI355X: Enable AITER and Expert Parallel#922
Open
ChuanLi1101 wants to merge 4 commits intoSemiAnalysisAI:mainfrom
Open
Optimize Kimi-K2.5-FP4 on AMD MI355X: Enable AITER and Expert Parallel#922ChuanLi1101 wants to merge 4 commits intoSemiAnalysisAI:mainfrom
ChuanLi1101 wants to merge 4 commits intoSemiAnalysisAI:mainfrom
Conversation
3 tasks
functionstackx
requested review from
Oseltamivir,
cquil11 and
functionstackx
and removed request for
functionstackx
…pace - Remove redundant VLLM_ROCM_USE_AITER_MLA=1 and VLLM_ROCM_USE_AITER_MOE=1 (both default to True in vllm envs.py, only master switch needed) - Remove VLLM_ROCM_USE_AITER_TRITON_ROPE=1 (noop without --compilation-config custom_ops+=+rotary_embedding) - Switch VLLM_ROCM_QUICK_REDUCE_QUANTIZATION from INT8 to INT4 for better TTFT/TPOT (2.2x vs 1.17x per quickreduce benchmarks) - Add TP8EP1 back to all search spaces alongside TP4EP1 and TP4EP4 so InferenceX can sweep and determine optimal config empirically Made-with: Cursor
Collaborator
|
/sweep test-config --config-files .github/configs/amd-master.yaml --runner-config .github/configs/runners.yaml --config-keys kimik2.5-fp4-mi355x-vllm |
Contributor
|
@seungrokj Kicking off a sweep. Run: https://github.com/SemiAnalysisAI/InferenceX/actions/runs/23416123849 |
seungrokj
reviewed
Mar 23, 2026
| --max-model-len $MAX_MODEL_LEN \ | ||
| --block-size=64 \ | ||
| --disable-log-requests \ | ||
| --block-size=1 \ |
Collaborator
There was a problem hiding this comment.
--no-enable-prefix-caching \
@ChuanLi1101 now we need this
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
6 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
VLLM_ROCM_USE_AITER=1,VLLM_ROCM_USE_AITER_MLA=1,VLLM_ROCM_USE_AITER_MOE=1, etc.)--enable-expert-parallelwhenEP_SIZE > 1, and add a correspondingtp: 4, ep: 4search-space entry in the benchmark config for ISL=1024/OSL=8192--gpu-memory-utilizationfrom 0.95 to 0.90 for stability, change--block-sizefrom 64 to 1HSA_NO_SCRATCH_RECLAIM=1) on older firmware (< 177) to avoid crashesChanged Files
.github/configs/amd-master.yamlkimik2.5-fp4-mi355x-vllmsearch spaces: tp 8->4, add ep=4 configbenchmarks/single_node/kimik2.5_fp4_mi355x.shTest Plan
kimik2.5-fp4-mi355x-vllmbenchmark suite on MI355X with the updated configEP_SIZE > 1) launches correctly with--enable-expert-parallel--gpu-memory-utilization 0.90and--block-size 1HSA_NO_SCRATCH_RECLAIMguard works