Skip to content

fix cp inference#4619

Merged
lvhan028 merged 2 commits into
InternLM:mainfrom
irexyc:fix-cp
May 28, 2026
Merged

fix cp inference#4619
lvhan028 merged 2 commits into
InternLM:mainfrom
irexyc:fix-cp

Conversation

@irexyc
Copy link
Copy Markdown
Collaborator

@irexyc irexyc commented May 25, 2026

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily receiving feedbacks. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.

Motivation

Please describe the motivation of this PR and the goal you want to achieve through this PR.

Modification

Please briefly describe what modification is made in this PR.

BC-breaking (Optional)

Does the modification introduce changes that break the backward-compatibility of the downstream repositories?
If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR.

Use cases (Optional)

If this PR introduces a new feature, it is better to list some use cases here, and update the documentation.

Checklist

  1. Pre-commit or other linting tools are used to fix the potential lint issues.
  2. The modification is covered by complete unit tests. If not, please add more unit tests to ensure the correctness.
  3. If the modification has a dependency on downstream projects of a newer version, this PR should be tested with all supported versions of downstream projects.
  4. The documentation has been modified accordingly, like docstring or example tutorials.

Copilot AI review requested due to automatic review settings May 25, 2026 04:31
Copy link
Copy Markdown
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

This PR addresses a context-parallel (CP) inference correctness issue in TurboMind’s LLaMA unified attention path by explicitly initializing the CP partial (M, L) reduction buffer to avoid stale values (e.g., when CTAs early-exit for finished sequences in async mode).

Changes:

  • Add a CUDA helper (invokeFillNegInfML) to initialize (M, L) pairs to (-inf, 0) before attention/reduction.
  • Call this initializer during UnifiedAttentionLayer::Run(BatchOp::kPrepare, ...) when CP is enabled.
  • Document the intent of the initializer in cp_utils.h.

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 3 comments.

File Description
src/turbomind/models/llama/unified_attention_layer.cc Calls the new CP partial buffer initializer during batch prepare.
src/turbomind/kernels/attention/cp_utils.h Declares invokeFillNegInfML with a new explanatory comment.
src/turbomind/kernels/attention/cp_utils.cu Implements the CUDA kernel + launcher to fill (M, L) pairs with (-inf, 0).

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comment on lines +29 to +38
void invokeFillNegInfML(float* data, size_t n_pairs, cudaStream_t stream)
{
if (n_pairs == 0) {
return;
}
constexpr int block = 256;
const size_t n_quads = n_pairs >> 1;
const size_t grid = (n_quads + block - 1) / block;
FillNegInfMLKernel<<<grid, block, 0, stream>>>(reinterpret_cast<float4*>(data), n_quads);
TM_CUDA_CHECK(cudaGetLastError());
Comment on lines +23 to +26
// Fill an array of (M, L) pairs with (-inf, 0). Used to initialize this rank's
// slot in `partial_ML` before attention, so that reduce treats slots left
// untouched by early-exiting CTAs (e.g. finished sequences in async mode) as
// no-contribution rather than reading stale data from previous batches.
Comment on lines 228 to +232
auto& d = data_.at(phase);
Clear(tmp_attn_.slice(0, d->decode.n + d->prefill.q_sum));
Clear(split_cnt_);
if (engine_param_.attn_cp_size > 1) {
invokeFillNegInfML(partial_ML_.data(), partial_ML_.size() / 2, core::Context::stream().handle());
@lvhan028 lvhan028 requested a review from lzhangzz May 25, 2026 04:50
@lvhan028 lvhan028 merged commit 6276b3b into InternLM:main May 28, 2026
9 of 10 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants