Activity
Fix prefix caching abstract type
Fix prefix caching abstract type
Adapt to flash-attention and fashinfer backend (previously only xform…
Adapt to flash-attention and fashinfer backend (previously only xform…
Fix type
Fix type
Fix rebase bug and static check error
Fix rebase bug and static check error
Delete block_table
Delete block_table
Fix call instances and yapf warning
Fix call instances and yapf warning
[Bugfix] Fix start_idx for computing slot mapping to avoid uninitiali…
[Bugfix] Fix start_idx for computing slot mapping to avoid uninitiali…
[Doc][4/N] Reorganize API Reference (vllm-project#11843)
[Doc][4/N] Reorganize API Reference (vllm-project#11843)
Address clang-format errors
Address clang-format errors
[Hardware][CPU] Refactor CPU vector types for ISAs
[Hardware][CPU] Refactor CPU vector types for ISAs
[V1] Enable profile for LLMEngine (vllm-project#10665)
[V1] Enable profile for LLMEngine (vllm-project#10665)
Break long lines and adjust imports
Break long lines and adjust imports
Force push
Break long lines
Break long lines
Force push
Break long lines
Break long lines
Merge remote-tracking branch 'origin/main' into Add-Arm-CPU-backend
Merge remote-tracking branch 'origin/main' into Add-Arm-CPU-backend
Resolve merge conflicts
Resolve merge conflicts
[Bugfix] bitsandbytes models fail to run pipeline parallel (vllm-proj…
[Bugfix] bitsandbytes models fail to run pipeline parallel (vllm-proj…
remove files
remove files
add username
add username
fix format
fix format
Merge branch 'main' into Convert-traces-to-perfetto-events
Merge branch 'main' into Convert-traces-to-perfetto-events
youkaichaopushed 31 commits to Convert-traces-to-perfetto-events • 6c97c34…97823b4 •
on Nov 10, 2024
Resolved merge conflicts
Resolved merge conflicts
[Misc] Fix typo in vllm-project#5895 (vllm-project#10145)
[Misc] Fix typo in vllm-project#5895 (vllm-project#10145)
[Misc] Address comments
[Misc] Address comments
[Doc] Fix references
[Doc] Fix references
[bugfix] fix chatglm dummy_data_for_glmv (vllm-project#9955)
[bugfix] fix chatglm dummy_data_for_glmv (vllm-project#9955)
[Hardward][CPU] Add ARM CPU backend
[Hardward][CPU] Add ARM CPU backend
Force push