Repository navigation
Tags
Tags
[ROCm][CI] Add MI355 dense NVFP4 and MoRI kernel mirrors (vllm-projec… …t#58281) Signed-off-by: Andreas Karatzas <akaratza@amd.com> Co-authored-by: OpenAI Codex <noreply@openai.com>
[CI][Build] Harden triton-cpu sleef submodule fetch in CPU image build ( vllm-project#57871) Signed-off-by: kimi-no-na-wa <kimi-no-na-wa@users.noreply.github.com> Co-authored-by: kimi-no-na-wa <kimi-no-na-wa@users.noreply.github.com>
[Bugfix][NIXL] Avoid receive reports for notification-only requests (v… …llm-project#57570) Signed-off-by: NickLucche <nicolo.lucchesi@mistral.ai> Co-authored-by: OpenAI Codex <codex@openai.com>
[Bugfix] Isolate supplemental FlashInfer BF16 autotuning (vllm-projec… …t#57285) Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com> Co-authored-by: OpenAI Codex <codex@openai.com>
vllm-proto 0.2.0 Validated by PR vllm-project#56538 CI at fa2a26f.
[watermarking] Dual-key gumbel-max watermarking for speculative decod… …ing support (vllm-project#56122) Signed-off-by: Raphael Rialland <raphael.rialland@mistral.ai> Signed-off-by: Simon Veitner <sveitner@redhat.com> Signed-off-by: Tomas Ruiz <tomas.ruiz.te@gmail.com> Co-authored-by: OpenAI Codex <codex@openai.com> Co-authored-by: Simon Veitner <sveitner@redhat.com> Co-authored-by: Tomas Ruiz <tomas.ruiz.te@gmail.com>
[Bugfix][Core] Apply dense prefix cache default to hybrid models (vll… …m-project#55861) Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
PreviousNext