Skip to content

[None][feat] Port GVR emission to the FP8 paged-MQA indexer scorer #18631

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.

Sign up for GitHub

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

Open
siyidNV wants to merge 3 commits into
base: main
Choose a base branch
from
Open

[None][feat] Port GVR emission to the FP8 paged-MQA indexer scorer #18631

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
861c397
[None][feat] port GVR emission to the FP8 paged-MQA indexer kernel
siyidNV Aug 13, 2026
5cf054e
[None][chore] Single-source the GVR emission epilogue and host valida…
siyidNV Sep 2, 2026
57c9918
[None][perf] Skip empty exact-claim bands on the block max
siyidNV Sep 3, 2026
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
2 changes: 0 additions & 2 deletions tensorrt_llm/_torch/attention_backend/sparse/dsa/indexer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -723,12 +723,10 @@ def __init__(
# GVR emission-assisted decode (opt-in, experimental): the FP4/FP8
# indexer epilogue emits candidates the GVR Top-K consumes (see
# gvr_emission / gvr_routing; state lives on the TopK module)
# only the FP4 scoring op accepts emission kwargs
self.use_gvr_emission = (
os.environ.get("TRTLLM_GVR_EMISSION", "0") == "1"
and decode_top_k_implementation == TopKImplementation.CUTE_DSL_GVR
and self.use_cute_dsl_paged_mqa_logits
and self.use_fp4
)

# Fused wk + weights_proj weight for single FP32 cuBLAS GEMM
Expand Down
Loading
Loading