Upgrading tvm-ffi/sgl-deep-gemm/tilelang

[Fridge003]

co-authored by @MartinHua

Motivation

Modifications

Accuracy Tests

Speed Tests and Profiling

Checklist

• Format your code according to the Format code with pre-commit.
• Add unit tests according to the Run and add unit tests.
• Update documentation according to Write documentations.
• Provide accuracy and speed benchmark results according to Test the accuracy and Benchmark the speed.
• Follow the SGLang code style guidance.

Review and Merge Process

1. Ping Merge Oncalls to start the process. See the PR Merge Process.
2. Get approvals from CODEOWNERS and other reviewers.
3. Trigger CI tests with comments or contact authorized users to do so.
   • Common commands include /tag-and-rerun-ci, /tag-run-ci-label, /rerun-failed-ci
4. After green CI and required approvals, ask Merge Oncalls or people with Write permission to merge the PR.

---

CI States

Latest PR Test (Base): ✅ Run #28483448041
Latest PR Test (Extra): ✅ Run #28483448031

[gemini-code-assist]

Code Review

This pull request updates the dependencies in pyproject.toml, upgrading apache-tvm-ffi from 0.1.9 to 0.1.11 and sgl-deep-gemm from 0.1.3 to 0.1.4rc0. I have no feedback to provide.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.

[Fridge003]

/rerun-test test/registered/disaggregation/test_disaggregation_hisparse.py

[github-actions]

Results for /rerun-test test/registered/disaggregation/test_disaggregation_hisparse.py:

🚀 8-gpu-h200 (1 test): ❌ View workflow run

cd test/ && python3 registered/disaggregation/test_disaggregation_hisparse.py

[Fridge003]

/rerun-test test/registered/quant/test_fp8_blockwise_gemm.py test/registered/disaggregation/test_disaggregation_hybrid_attention.py test/registered/radix_cache/unified_radix_tree/test_unified_radix_cache_kl_dsv4.py python/sglang/multimodal_gen/test/server/test_server_1_gpu.py

[github-actions]

Results for /rerun-test test/registered/quant/test_fp8_blockwise_gemm.py test/registered/disaggregation/test_disaggregation_hybrid_attention.py test/registered/radix_cache/unified_radix_tree/test_unified_radix_cache_kl_dsv4.py python/sglang/multimodal_gen/test/server/test_server_1_gpu.py:

🚀 4-gpu-b200 (1 test): ❌ View workflow run

cd test/ && python3 registered/quant/test_fp8_blockwise_gemm.py

🚀 8-gpu-h200 (1 test): ✅ View workflow run

cd test/ && python3 registered/disaggregation/test_disaggregation_hybrid_attention.py

🚀 4-gpu-h100 (1 test): ✅ View workflow run

cd test/ && python3 registered/radix_cache/unified_radix_tree/test_unified_radix_cache_kl_dsv4.py

🚀 1-gpu-h100 (1 test): ❌ View workflow run

python3 -m pytest python/sglang/multimodal_gen/test/server/test_server_1_gpu.py -x

[Fridge003]

/rerun-test test/registered/jit/test_hisparse.py

[github-actions]

Results for /rerun-test test/registered/jit/test_hisparse.py:

🚀 1-gpu-h100 (1 test): ✅ View workflow run

cd test/ && python3 registered/jit/test_hisparse.py

[Fridge003]

/rerun-test python/sglang/multimodal_gen/test/server/test_server_1_gpu.py

[github-actions]

Results for /rerun-test python/sglang/multimodal_gen/test/server/test_server_1_gpu.py:

🚀 1-gpu-h100 (1 test): ❌ View workflow run

python3 -m pytest python/sglang/multimodal_gen/test/server/test_server_1_gpu.py -x

[Fridge003]

/rerun-test test/registered/models_e2e/test_deepseek_v4_flash_fp4_megamoe_b200.py

[github-actions]

Results for /rerun-test test/registered/models_e2e/test_deepseek_v4_flash_fp4_megamoe_b200.py:

🚀 4-gpu-b200 (1 test): ❌ View workflow run

cd test/ && python3 registered/models_e2e/test_deepseek_v4_flash_fp4_megamoe_b200.py