[PR #447] [CLOSED] Fix bug on hybrid-ep #575

New issue

Closed

opened 2026-10-27 21:04:11 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-27 21:04:11 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/deepseek-ai/DeepEP/pull/447
Author: @Autumn1998
Created: 10/10/2025
Status: ❌ Closed

Base: main ← Head: tongliu/fix_bug

📝 Commits (10+)

c9f647d Add HybridEP (#420)
6ad6896 add document of Hybrid-EP (#428)
476ad70 [Feature] Support normal mode for non-nvlink environment (#375)
e713f52 fix issue with align, recover format for csrc/kernels/internode.cu and (#431)
c5a3e9b Add Jit compiler (#433)
f4f2c10 add permute/unpermute, add sync free, refactor (#439)
85fba86 Jershi/fp4 intranode ready (#339)
0ed15b5 fix bug on token drop (#443)
2e92368 fix bug if num_dispatched_tokens = 0
4ef04b2 fix bug on open handlr for scale

📊 Changes

34 files changed (+8765 additions, -134 deletions)

View changed files

➕ Hybrid-EP_Intra-node_Implementation.md (+217 -0)
📝 README.md (+3 -0)
📝 csrc/config.hpp (+26 -0)
📝 csrc/deep_ep.cpp (+434 -35)
📝 csrc/deep_ep.hpp (+25 -4)
➕ csrc/hybrid_ep/allocator/allocator.cu (+122 -0)
➕ csrc/hybrid_ep/allocator/allocator.cuh (+47 -0)
➕ csrc/hybrid_ep/backend/hybrid_ep_backend.cuh (+2528 -0)
➕ csrc/hybrid_ep/config.cuh (+60 -0)
➕ csrc/hybrid_ep/executor/executor.cu (+303 -0)
➕ csrc/hybrid_ep/executor/executor.cuh (+96 -0)
➕ csrc/hybrid_ep/extension/permute.cu (+626 -0)
➕ csrc/hybrid_ep/extension/permute.cuh (+117 -0)
➕ csrc/hybrid_ep/hybrid_ep.cu (+642 -0)
➕ csrc/hybrid_ep/hybrid_ep.cuh (+102 -0)
➕ csrc/hybrid_ep/jit/compiler.cu (+311 -0)
➕ csrc/hybrid_ep/jit/compiler.cuh (+98 -0)
➕ csrc/hybrid_ep/pybind_hybrid_ep.cu (+113 -0)
➕ csrc/hybrid_ep/utils.cuh (+164 -0)
📝 csrc/kernels/CMakeLists.txt (+2 -1)

...and 14 more files

📄 Description

fix bug if no tokens received on the local rank.

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/deepseek-ai/DeepEP/pull/447 **Author:** [@Autumn1998](https://github.com/Autumn1998) **Created:** 10/10/2025 **Status:** ❌ Closed **Base:** `main` ← **Head:** `tongliu/fix_bug` --- ### 📝 Commits (10+) - [`c9f647d`](https://github.com/deepseek-ai/DeepEP/commit/c9f647dd4108539e32d4375c932d0d44279d45ba) Add HybridEP (#420) - [`6ad6896`](https://github.com/deepseek-ai/DeepEP/commit/6ad6896ddcc4f02531a008851006af1e191d9cd4) add document of Hybrid-EP (#428) - [`476ad70`](https://github.com/deepseek-ai/DeepEP/commit/476ad704133e04942ce113ec3ffdd028abb2fa5e) [Feature] Support normal mode for non-nvlink environment (#375) - [`e713f52`](https://github.com/deepseek-ai/DeepEP/commit/e713f5296157e6e0d7d465b1f2d13383a8791d93) fix issue with align, recover format for csrc/kernels/internode.cu and (#431) - [`c5a3e9b`](https://github.com/deepseek-ai/DeepEP/commit/c5a3e9b790caedecfe362bc206c186185d8bfaab) Add Jit compiler (#433) - [`f4f2c10`](https://github.com/deepseek-ai/DeepEP/commit/f4f2c10aa57d3155a1320b0c26a6e70d5746d204) add permute/unpermute, add sync free, refactor (#439) - [`85fba86`](https://github.com/deepseek-ai/DeepEP/commit/85fba86d7f6e3e6e04d19af3cfd7929622facdff) Jershi/fp4 intranode ready (#339) - [`0ed15b5`](https://github.com/deepseek-ai/DeepEP/commit/0ed15b59f0f1d61504cc7e29d79e8c219b8b0e0a) fix bug on token drop (#443) - [`2e92368`](https://github.com/deepseek-ai/DeepEP/commit/2e9236852b6646697e1910bce210ec2adad9bca8) fix bug if num_dispatched_tokens = 0 - [`4ef04b2`](https://github.com/deepseek-ai/DeepEP/commit/4ef04b2e0b515c9219e94276988ab1aae9e7120d) fix bug on open handlr for scale ### 📊 Changes **34 files changed** (+8765 additions, -134 deletions) <details> <summary>View changed files</summary> ➕ `Hybrid-EP_Intra-node_Implementation.md` (+217 -0) 📝 `README.md` (+3 -0) 📝 `csrc/config.hpp` (+26 -0) 📝 `csrc/deep_ep.cpp` (+434 -35) 📝 `csrc/deep_ep.hpp` (+25 -4) ➕ `csrc/hybrid_ep/allocator/allocator.cu` (+122 -0) ➕ `csrc/hybrid_ep/allocator/allocator.cuh` (+47 -0) ➕ `csrc/hybrid_ep/backend/hybrid_ep_backend.cuh` (+2528 -0) ➕ `csrc/hybrid_ep/config.cuh` (+60 -0) ➕ `csrc/hybrid_ep/executor/executor.cu` (+303 -0) ➕ `csrc/hybrid_ep/executor/executor.cuh` (+96 -0) ➕ `csrc/hybrid_ep/extension/permute.cu` (+626 -0) ➕ `csrc/hybrid_ep/extension/permute.cuh` (+117 -0) ➕ `csrc/hybrid_ep/hybrid_ep.cu` (+642 -0) ➕ `csrc/hybrid_ep/hybrid_ep.cuh` (+102 -0) ➕ `csrc/hybrid_ep/jit/compiler.cu` (+311 -0) ➕ `csrc/hybrid_ep/jit/compiler.cuh` (+98 -0) ➕ `csrc/hybrid_ep/pybind_hybrid_ep.cu` (+113 -0) ➕ `csrc/hybrid_ep/utils.cuh` (+164 -0) 📝 `csrc/kernels/CMakeLists.txt` (+2 -1) _...and 14 more files_ </details> ### 📄 Description 1. fix bug if no tokens received on the local rank. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi

2026-10-27 21:04:11 +00:00

closed this issue
added the
pull-request
label

No labels

pull-request

No milestone

No project

No assignees

1 participant

Notifications

Due date

The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference

deepseek-ai/DeepEP#575

No description provided.

Rows
Columns