Skip to content

Tags: qizwiz/vllm

Tags

v0.21.1rc0

Toggle v0.21.1rc0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
[ROCm][CI] Stage B gating (vllm-project#42025)

Signed-off-by: Andreas Karatzas <akaratza@amd.com>

v0.21.0

Toggle v0.21.0's commit message
[Bugfix] Fix DeepSeek V4 MTP HC state handling (vllm-project#42320)

Signed-off-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
(cherry picked from commit f1cc7aa)

v0.21.0rc3

Toggle v0.21.0rc3's commit message
[MLA Attention Backend] Add TOKENSPEED_MLA backend for DSR1/Kimi K25 …

…prefill + decode on Blackwell (vllm-project#41778)

Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
(cherry picked from commit 0d2732d)

v0.21.0rc2

Toggle v0.21.0rc2's commit message
[Bugfix] Install nvidia-cutlass-dsl[cu13] extra on CUDA 13 platforms (v…

…llm-project#42438)

Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
(cherry picked from commit 140dc2e)

v0.21.0rc1

Toggle v0.21.0rc1's commit message
[Build] Build bundled DeepGEMM `_C` per-Python so the wheel imports o…

…n every CPython (vllm-project#41516)

Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
(cherry picked from commit d077622)

v0.20.2

Toggle v0.20.2's commit message
[CI] Automate Docker Hub release image publishing (vllm-project#40415)

Signed-off-by: khluu <khluu000@gmail.com>
(cherry picked from commit 1333864)

v0.20.1

Toggle v0.20.1's commit message
Revert "[DSv4] Use `cvt` PTX for FP32->FP4 conversion (vllm-project#4…

…1015)"

This reverts commit d9f3961.

v0.20.2rc0

Toggle v0.20.2rc0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
[MRV2] Add shutdown() method (vllm-project#41297)

Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>

v0.20.1rc0

Toggle v0.20.1rc0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Add system_fingerprint field to OpenAI-compatible API responses (vllm…

…-project#40537)

Co-authored-by: Claude <noreply@anthropic.com>

v0.20.0

Toggle v0.20.0's commit message
[Docker] Install numactl CLI in CUDA runtime image (vllm-project#41032)

Signed-off-by: Zhewen Li <zhewenli@inferact.ai>
Co-authored-by: Zhewen Li <zhewenli@inferact.ai>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
(cherry picked from commit 6232fb4)