Chun reima/sglang fp8 v0.5.8 mi355#572
Merged
functionstackx merged 5 commits intomainfrom Jan 27, 2026
Merged
Conversation
1. activate FP8 KV cache 2. use the MLA persistent kernel
Contributor
|
@pr-claude review plz |
Contributor
|
Claude finished @functionstackx's task in 51s —— View job PR Review Complete
Summary: This PR updates the MI355X DeepSeek R1 FP8 SGLang Docker image from v0.5.5.post3 to v0.5.8. The master config change is properly accompanied by a perf-changelog entry. I left one suggestion: the perf-changelog description should mention the key fix (disabling MLA persistent kernel when not using fp8 kv_cache) as noted in the PR body and requested by @functionstackx in the inline comment. No blocking issues found. |
Add description: Disables mla persistent kernel when not using fp8 kv_cache Co-authored-by: functionstackx <functionstackx@users.noreply.github.com>
Contributor
|
e2e tests here already so cancelled sweep-enabled https://github.com/InferenceMAX/InferenceMAX/actions/runs/21399947035 |
cquil11
pushed a commit
that referenced
this pull request
Jan 29, 2026
* Update SGLang Docker Image for MI355 to v0.5.8 1. activate FP8 KV cache 2. use the MLA persistent kernel * Do not activate FP8 KV cache and the MLA persistent kernel explicitly * Add config-keys (v0.5.5.post3 --> v0.5.8) * Update perf-changelog.yaml with key fix description for v0.5.8 Add description: Disables mla persistent kernel when not using fp8 kv_cache Co-authored-by: functionstackx <functionstackx@users.noreply.github.com> --------- Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com> Co-authored-by: functionstackx <functionstackx@users.noreply.github.com> Co-authored-by: functionstackx <47992694+functionstackx@users.noreply.github.com>
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
3 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.
Update MI355X DeepSeek R1 FP8 SGLang image from v0.5.5.post3 to v0.5.8
Key fix: Disable mla persistent kernel when not using fp8 kv_cache (sgl-project/sglang#17327)
Contributor list: