8000 History for cmake - ayghri/vllm · GitHub

Repository navigation

Commits

History for

Commits on May 9, 2026
- Require C++20 for compatibility with PyTorch (#40380)
  
  r-barnes
  and
  claude
  authored
  d6563d6
Commits on May 7, 2026
- [CPU] Bump up to the latest CPU kernels (#41924)
  bigPYJ1151
  authored
  b3945cc
Commits on May 6, 2026
- [Feat] dnnl build for AVX2 W8A8 Int8 (#41318)
  
  tianmu-li
  and
  bigPYJ1151
  authored
  e87e09a
- [Build] Fall back to system libgomp when torch has no vendored copy (#40575)
  
  lyd1992
  and
  claude
  authored
aee190a

Commits on May 2, 2026

Revert "[Build] Make bundled DeepGEMM wheel portable across Python versions" (#41512)
mgoin
authored
0a9362d

Commits on May 1, 2026

[Build] Make bundled DeepGEMM wheel portable across Python versions (#41476)
mgoin
authored
0c99629

Commits on Apr 27, 2026

[Feat] DeepSeek V4 Rebased (#40860)

authored
4d51588

Commits on Apr 20, 2026

[CPU][RISC-V] Support multiple RVV VLEN targets via compile-time dispatch (#39478)
velonica0
authored
ec7aafc

Commits on Apr 17, 2026

[CPU] Refactor CPU affinity and memory management (#39781)
bigPYJ1151
authored
d02421a

Commits on Apr 16, 2026

[perf][cpu] Accelerate BF16 GELU with LUT impl on Arm CPUs (#37469)

fadara01
and
mergify[bot]
authored
445b709

Commits on Apr 10, 2026

feat(cpu): add CPU support for draft model speculative decoding (#32662)
ganeshr10
authored
445a2a4

Commits on Apr 9, 2026

[UX] Integrate DeepGEMM into vLLM wheel via CMake (#37980)

mgoin
and
claude
authored
eb4205f

Commits on Apr 8, 2026

Commits on Apr 2, 2026

[FA4] Update flash-attention to latest upstream FA4 (#38690)
LucasWilkinson
authored
cb3935a

Commits on Mar 31, 2026

[CPU] Support int8 compute mode in CPU AWQ (#35697)
yintong-lu
authored
f09daea

Commits on Mar 27, 2026

[NVIDIA] Fix DGX Spark logic (#38126)

authored
97d1919

Commits on Mar 25, 2026

[Bugfix] Preserve CUDA arch suffix (a/f) for SM12x — fixes NVFP4 NaN on desktop Blackwell (#37725)

RobTand
and
LucasWilkinson
authored
4a76ad1

Commits on Mar 17, 2026

pick up tuned prefill configs for FP8 FA3 (#36265)
jmkuebler
authored
77d2a5f

Commits on Mar 14, 2026

[UX] Improve UX of CPU backend (#36968)

bigPYJ1151
and
gemini-code-assist[bot]
authored
092ace9

Commits on Mar 12, 2026

[Attention] Use FA4 for MLA prefill (#34732)
MatthewBonanni
authored
f444c05

Commits on Mar 11, 2026

feat: add RISC-V support for CPU backend (v2) (#36578)

typer-J
and
bigPYJ1151
authored
4184653

Commits on Mar 6, 2026

cpu: aarch64: Upgrade OneDNN for aarch64 to add support for int8 matmul (#36147)
nikhil-arm
authored
0a49676

Commits on Mar 3, 2026

[BugFix] Fix cmake based incremental install (wrong vllm install dir) (#35773)

LucasWilkinson
and
yewentao256
authored
f44d1dd

Commits on Mar 1, 2026

[Attention] FA4 integration (#32974)

authored
8b5014d

Commits on Feb 28, 2026

[CI/Build] CPU release supports both of AVX2 and AVX512 (#35466)

majian4work
and
bigPYJ1151
authored
90805ff

Commits on Feb 16, 2026

[BugFix] Fix Python 3.13 FlashMLA import error (#34548)

LucasWilkinson
and
jeejeelee
authored
bb85929

Commits on Feb 15, 2026

[CPU][ARM] Add ARM BF16 cross-compilation support and improve documen… (#33079)

maryamtahhan
and
bigPYJ1151
authored
f07a128

Commits on Feb 11, 2026

Reapply [Attention][FA3] Update FA3 to include new swizzle optimization (#34043)
LucasWilkinson
authored
c7914d3

Commits on Feb 8, 2026

[Release 2.10] Update to Torch 2.10 - final release (#30525)
atalman
authored
f97ca67

Commits on Feb 5, 2026

Revert "[Attention][FA3] Update FA3 to include new swizzle optimization" (#33841)
ProExpertProg
authored
e3bf79f

Commits on Feb 4, 2026

[CPU] Split attention dispatch by head_dim alignment (#32161)
R3hankhan123
authored
4dffc5e

Commits on Feb 3, 2026

[Attention][FA3] Update FA3 to include new swizzle optimization (#23465)
LucasWilkinson
authored
2267cb1

Commits on Jan 24, 2026

[CPU] Improve CPU Docker build (#30953)

maryamtahhan
and
bigPYJ1151
authored
203d0bc

Commits on Jan 22, 2026

[CPU Backend] [Perf] Accelerate tensor-parallel/data-parallel inference across NUMA domains on Arm (#32792)
fadara01
authored
744ef30

0