[None][chore] Update flashinfer-python from 0.6.14 to 0.6.15 - #16530
Conversation
Bump flashinfer-python dependency to the latest stable release. Updated version pins in requirements.txt, security_scanning/pyproject.toml, and ATTRIBUTIONS-Python.md. Signed-off-by: yihwang-nv <yihwang@nvidia.com>
📝 WalkthroughWalkthroughChangesFlashInfer version update
Estimated code review effort: 1 (Trivial) | ~2 minutes Suggested reviewers: 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
…r 0.6.15 flashinfer 0.6.15 includes the fix for the missing multi-CTAs counter buffer initialization (flashinfer-ai/flashinfer#3433). Remove the _clear_multi_ctas_kv_counter_workspace workaround calls from run_generation() and run_mla_generation(), and drop the now-unused helper functions _clear_multi_ctas_kv_counter_workspace and _get_multi_ctas_kv_counter_size. Signed-off-by: yihwang-nv <yihwang@nvidia.com>
|
/bot run --disable-fail-fast --add-multi-gpu-test |
|
PR_Github #59920 [ run ] triggered by Bot. Commit: |
|
PR_Github #59920 [ run ] completed with state
|
|
/bot run --disable-fail-fast --add-multi-gpu-test |
|
PR_Github #60180 [ run ] triggered by Bot. Commit: |
|
PR_Github #60180 [ run ] completed with state
|
Signed-off-by: yihwang-nv <yihwang@nvidia.com>
|
/bot run --disable-fail-fast --add-multi-gpu-test |
|
PR_Github #60286 [ run ] triggered by Bot. Commit: |
|
PR_Github #60286 [ run ] completed with state
|
|
/bot run --disable-fail-fast --add-multi-gpu-test |
|
PR_Github #60356 [ run ] triggered by Bot. Commit: |
|
PR_Github #60356 [ run ] completed with state
|
|
/bot run --disable-fail-fast --add-multi-gpu-test |
|
PR_Github #60548 [ run ] triggered by Bot. Commit: |
|
PR_Github #60548 [ run ] completed with state |
|
PR_Github #60615 [ run ] triggered by Bot. Commit: |
|
PR_Github #60615 [ run ] completed with state |
Summary
Test plan
Summary by CodeRabbit