[PR #4] [CLOSED] [DONT MERGE] [PD] Add raise exception for mooncake #2

New issue

Closed

opened 2026-10-29 21:06:23 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-29 21:06:23 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/kvcache-ai/sglang/pull/4
Author: @stmatengss
Created: 4/10/2025
Status: ❌ Closed

Base: main ← Head: add_raise_mooncake_exception

📝 Commits (10+)

11ac5a4 [PD] Add raise exception for mooncake
654e0df Merge remote-tracking branch 'origin' into add_raise_mooncake_exception
c163bf4 chore: bump sgl-kernel v0.0.8.post1 (#5289)
c35dcfd [PD] fix: skip warmup request in disaggregation mode to prevent crash on timeout (#5292)
4aa6bab [Docs] Supported Model Docs - Major restructuring (#5290)
80aa8ca fix: update update_wheel_index for cu128 (#5300)
a0a9f6d [Docs] Remove the older supported docs section (#5301)
60bcbf2 remove moe_align_block_size torch.zeros in small batch/expert mode (#5298)
f774a0d feat: add blackwell Dockerfile (#5302)
6f85937 feat: add blackwell workflow (#5303)

📊 Changes

81 files changed (+2870 additions, -1110 deletions)

View changed files

📝 .github/workflows/pr-test-sgl-kernel.yml (+19 -7)
➕ .github/workflows/release-docker-blackwell.yml (+36 -0)
📝 .github/workflows/release-pypi-kernel.yml (+1 -1)
📝 .github/workflows/release-whl-kernel-cu128.yml (+1 -1)
📝 .github/workflows/release-whl-kernel.yml (+1 -1)
📝 .gitmodules (+0 -4)
📝 README.md (+1 -1)
📝 benchmark/kernels/fused_moe_triton/README.md (+10 -2)
📝 benchmark/mmmu/bench_sglang.py (+0 -1)
📝 benchmark/mmmu/eval_utils.py (+20 -10)
➕ docker/Dockerfile.blackwell (+208 -0)
📝 docker/Dockerfile.dev (+1 -0)
📝 docker/Dockerfile.sagemaker (+1 -73)
📝 docs/backend/openai_api_vision.ipynb (+1 -1)
📝 docs/backend/server_arguments.md (+2 -1)
📝 docs/backend/structured_outputs.ipynb (+35 -4)
📝 docs/frontend/frontend.ipynb (+1 -1)
📝 docs/index.rst (+10 -0)
📝 docs/references/general.rst (+0 -1)
➖ docs/references/supported_models.md (+0 -145)

...and 61 more files

📄 Description

Motivation

Modifications

Checklist

Format your code according to the Code Formatting with Pre-Commit.
Add unit tests as outlined in the Running Unit Tests.
Update documentation / docstrings / example tutorials as needed, according to Writing Documentation.
Provide throughput / latency benchmark results and accuracy evaluation results as needed, according to Benchmark and Profiling and Accuracy Results.
For reviewers: If you haven't made any contributions to this PR and are only assisting with merging the main branch, please remove yourself as a co-author when merging the PR.
Please feel free to join our Slack channel at https://slack.sglang.ai to discuss your PR.

_{🔄 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/kvcache-ai/sglang/pull/4 **Author:** [@stmatengss](https://github.com/stmatengss) **Created:** 4/10/2025 **Status:** ❌ Closed **Base:** `main` ← **Head:** `add_raise_mooncake_exception` --- ### 📝 Commits (10+) - [`11ac5a4`](https://github.com/kvcache-ai/sglang/commit/11ac5a440821edbebf586549ca78ae933c3ff1c7) [PD] Add raise exception for mooncake - [`654e0df`](https://github.com/kvcache-ai/sglang/commit/654e0df4cdf313e427492ec1353db00ed52b00f2) Merge remote-tracking branch 'origin' into add_raise_mooncake_exception - [`c163bf4`](https://github.com/kvcache-ai/sglang/commit/c163bf4ff16235536832f54a7512b69bc03825c5) chore: bump sgl-kernel v0.0.8.post1 (#5289) - [`c35dcfd`](https://github.com/kvcache-ai/sglang/commit/c35dcfdb30cc3839acb503f6dd739fce86a66e15) [PD] fix: skip warmup request in disaggregation mode to prevent crash on timeout (#5292) - [`4aa6bab`](https://github.com/kvcache-ai/sglang/commit/4aa6bab0b060978b2650da44cc03bf0724eec537) [Docs] Supported Model Docs - Major restructuring (#5290) - [`80aa8ca`](https://github.com/kvcache-ai/sglang/commit/80aa8ca84eb4391bc14e4fa2f4e85999b5c1e14f) fix: update update_wheel_index for cu128 (#5300) - [`a0a9f6d`](https://github.com/kvcache-ai/sglang/commit/a0a9f6d64f084a5a869c50633aae50e90f2824ef) [Docs] Remove the older supported docs section (#5301) - [`60bcbf2`](https://github.com/kvcache-ai/sglang/commit/60bcbf2a35e290a351386f4dbe85f5b0534acb14) remove moe_align_block_size torch.zeros in small batch/expert mode (#5298) - [`f774a0d`](https://github.com/kvcache-ai/sglang/commit/f774a0d2755787a3efc7a640bc56bd924079d280) feat: add blackwell Dockerfile (#5302) - [`6f85937`](https://github.com/kvcache-ai/sglang/commit/6f8593799bd10234053ecafa4eb974bb430e8573) feat: add blackwell workflow (#5303) ### 📊 Changes **81 files changed** (+2870 additions, -1110 deletions) <details> <summary>View changed files</summary> 📝 `.github/workflows/pr-test-sgl-kernel.yml` (+19 -7) ➕ `.github/workflows/release-docker-blackwell.yml` (+36 -0) 📝 `.github/workflows/release-pypi-kernel.yml` (+1 -1) 📝 `.github/workflows/release-whl-kernel-cu128.yml` (+1 -1) 📝 `.github/workflows/release-whl-kernel.yml` (+1 -1) 📝 `.gitmodules` (+0 -4) 📝 `README.md` (+1 -1) 📝 `benchmark/kernels/fused_moe_triton/README.md` (+10 -2) 📝 `benchmark/mmmu/bench_sglang.py` (+0 -1) 📝 `benchmark/mmmu/eval_utils.py` (+20 -10) ➕ `docker/Dockerfile.blackwell` (+208 -0) 📝 `docker/Dockerfile.dev` (+1 -0) 📝 `docker/Dockerfile.sagemaker` (+1 -73) 📝 `docs/backend/openai_api_vision.ipynb` (+1 -1) 📝 `docs/backend/server_arguments.md` (+2 -1) 📝 `docs/backend/structured_outputs.ipynb` (+35 -4) 📝 `docs/frontend/frontend.ipynb` (+1 -1) 📝 `docs/index.rst` (+10 -0) 📝 `docs/references/general.rst` (+0 -1) ➖ `docs/references/supported_models.md` (+0 -145) _...and 61 more files_ </details> ### 📄 Description  ## Motivation  ## Modifications  ## Checklist - [ ] Format your code according to the [Code Formatting with Pre-Commit](https://docs.sglang.ai/references/contribution_guide.html#code-formatting-with-pre-commit). - [ ] Add unit tests as outlined in the [Running Unit Tests](https://docs.sglang.ai/references/contribution_guide.html#running-unit-tests-adding-to-ci). - [ ] Update documentation / docstrings / example tutorials as needed, according to [Writing Documentation](https://docs.sglang.ai/references/contribution_guide.html#writing-documentation-running-docs-ci). - [ ] Provide throughput / latency benchmark results and accuracy evaluation results as needed, according to [Benchmark and Profiling](https://docs.sglang.ai/references/benchmark_and_profiling.html) and [Accuracy Results](https://docs.sglang.ai/references/accuracy_evaluation.html). - [ ] For reviewers: If you haven't made any contributions to this PR and are only assisting with merging the main branch, please remove yourself as a co-author when merging the PR. - [ ] Please feel free to join our Slack channel at https://slack.sglang.ai to discuss your PR. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi added the

pull-request

label

2026-10-29 21:06:23 +00:00

bsakaguchi referenced this issue

2026-10-29 21:06:23 +00:00

[PR #2] [CLOSED] Support different tp_size - Part 1 p/d dynamic connection #3

bsakaguchi closed this issue

2026-10-29 21:06:24 +00:00

bsakaguchi referenced this issue

2026-10-29 21:06:43 +00:00

[PR #45] fix(v4-flash): make ExpertDistributionRecorder work for DeepSeek-V4-Flash #45