perf(gfx12): disable slow default DFlash verify graph - #708
Open
HUSRCF wants to merge 1 commit into
Open
Conversation
6 tasks
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Disable the default DFlash verifier HipGraph route for
gfx1201 + MQ4G256.Paired long-context runs on an R9700 showed the captured verifier graph slower than the direct tiled-flash verifier path. The graph remains available through the explicit diagnostic opt-in:
Other architectures and quantization shapes retain their existing behavior.
Which surface(s) does this touch?
hipfire-arch-qwen35Implementation
dflash_verify_graph_env_eligible()is default-off only forgfx1201 + MQ4G256. Explicit behavior remains:HIPFIRE_VERIFY_GRAPH=0: force graph offHIPFIRE_VERIFY_GRAPH=1: diagnostic graph opt-inThe direct batched tiled-flash verifier path remains enabled.
Tests
cargo test -p hipfire-arch-qwen35 --lib dflash_verify_graph_env -- --nocapturecargo build --release -p hipfire-cli -p hipfire-daemonmax-seq=32768,max-tokens=1024, approximately 11.5K-token promptsHIP_VISIBLE_DEVICES=0E2E result:
All requests completed with
finish=stop; no attractor or empty-output failures were reported.Battery output:
/tmp/hf693-gfx12-latest-e2e.jsonGraph opt-in validation
A separate one-request run with
HIPFIRE_VERIFY_GRAPH=1confirmed:The opt-in request produced the same output identity as the default route (
request_md5=8460b63690bf124ed759f90efdb777f3, 299 tokens,tau=4.84,finish=stop).Artifacts
{"routes":[{"mode":"battery","tag":"qwen3.6:27b"}],"claim":"On gfx1201 with Qwen3.6 27B MQ4 DFlash, the legacy MQ4 verifier Graph is disabled by default while the direct tiled-flash verifier remains active; HIPFIRE_VERIFY_GRAPH=1 still captures the diagnostic graph."}