Commits

Breadcrumbs

History for

onmain

User selector

All users

Datepicker

All time

Commit History

Commits on Aug 28, 2024

• [Kernel/Model] Migrate mamba_ssm and causal_conv1d kernels to vLLM (vllm-project#7651)

  mzusman

  authored
  fdd9daa

Commits on Aug 27, 2024

• [Kernel] Expand MoE weight loading + Add Fused Marlin MoE Kernel (vllm-project#7766)

  Show description for fc91188
  

  dsikka

  and

  ElizaWszola

  authored
  fc91188

Commits on Aug 22, 2024

• [Bugfix] Don't build machete on cuda <12.0 (vllm-project#7757)

  LucasWilkinson

  authored
  55d63b1

• Revert "[Kernel] Expand MoE weight loading + Add Fused Marlin MoE Kernel (vllm-project#7527)" (vllm-project#7764)

  mgoin

  authored
  aae74ef

Commits on Aug 21, 2024

• [Kernel] Expand MoE weight loading + Add Fused Marlin MoE Kernel (vllm-project#7527)

  Show description for 8678a69
  

  dsikka

  and

  ElizaWszola

  authored
  8678a69

• [Bugfix] Pass PYTHONPATH from setup.py to CMake (vllm-project#7730)

  sasha0552

  authored
  1b32e02

Commits on Aug 20, 2024

• [Kernel] (1/N) Machete - Hopper Optimized Mixed Precision Linear Kernel (vllm-project#7174)

  LucasWilkinson

  authored
  5288c06

Commits on Aug 12, 2024

• [CI/Build] bump minimum cmake version (vllm-project#6999)

  dtrifiro

  authored
  774cd1d

Commits on Aug 5, 2024

• [Core] Support loading GGUF model (vllm-project#5191)

  Show description for 360bd67
  

  Isotr0py

  and

  mgoin

  authored
  360bd67

• [Bugfix][CI/Build] Fix CUTLASS FetchContent (vllm-project#7171)

  tlrmchlsmth

  authored
  4cf1dc3

• [Kernel] Update CUTLASS to 3.5.1 (vllm-project#7085)

  tlrmchlsmth

  authored
  8571ac4

Commits on Aug 2, 2024

• [Misc] Disambiguate quantized types via a new ScalarType (vllm-project#6396)

  LucasWilkinson

  authored
  a8d604c

• [CI/Build] Add support for Python 3.12 (vllm-project#7035)

  mgoin

  authored
  b482b9a

Commits on Aug 1, 2024

• [CI/Build][Bugfix] Fix CUTLASS header-only line (vllm-project#7034)

  tlrmchlsmth

  authored
  6a11fdf

• [CI/Build] Update PyTorch to 2.4.0 (vllm-project#6951)

  Show description for 7e0861b
  

  SageMoore

  and

  mgoin

  authored
  7e0861b

• [Kernel][RFC] Refactor the punica kernel based on Triton (vllm-project#5036)

  jeejeelee

  authored
  7ecee34

Commits on Jul 31, 2024

• Support W4A8 quantization for vllm (vllm-project#5218)

  HandH1998

  authored
  6512937

Commits on Jul 21, 2024

• [Kernel][Core] Add AWQ support to the Marlin kernel (vllm-project#6612)

  alexm-neuralmagic

  authored
  396d92d

Commits on Jul 20, 2024

• [Bugfix][CI/Build][Hardware][AMD] Fix AMD tests, add HF cache, update CK FA, add partially supported model notes (vllm-project#6543)

  mawong-amd

  authored
  06d6c5f

Commits on Jul 17, 2024

• [Core] draft_model_runner: Implement prepare_inputs on GPU for advance_step (vllm-project#6338)

  alexm-neuralmagic

  authored
  e76466d

Commits on Jul 12, 2024

• [MISC] Upgrade dependency to PyTorch 2.3.1 (vllm-project#5327)

  comaniac

  authored
  aa48e50

Commits on Jul 3, 2024

• [Kernel] Expand FP8 support to Ampere GPUs using FP8 Marlin (vllm-project#5975)

  mgoin

  authored
  47f0954

Commits on Jun 26, 2024

• [Kernel] Adding bias epilogue support for cutlass_scaled_mm (vllm-project#5560)

  Show description for 5bfd1bb
  

  3 peopleauthored
  5bfd1bb

Commits on Jun 25, 2024

• [Hardware][AMD][CI/Build][Doc] Upgrade to ROCm 6.1, Dockerfile improvements, test fixes (vllm-project#5422)

  mawong-amd

  authored
  dd793d1

Commits on Jun 13, 2024

• [Kernel] Factor out epilogues from cutlass kernels (vllm-project#5391)

  Show description for 85657b5
  

  5 peopleauthored
  85657b5

Commits on Jun 9, 2024

• [Kernel][Misc] Use TORCH_LIBRARY instead of PYBIND11_MODULE for custom ops (vllm-project#5047)

  bnellnm

  authored
  5467ac3

Commits on Jun 2, 2024

• [Kernel][ROCm][AMD] enable fused topk_softmax kernel for moe layer (vllm-project#4927)

  Show description for a66cf40
  divakar-amd

  authored
  a66cf40

Commits on May 31, 2024

• Fix cutlass sm_90a vesrion in CMakeList

  simon-mo

  committed
  533c217

Commits on May 30, 2024

• [Build] Disable sm_90a in cu11 (vllm-project#5141)

  simon-mo

  authored
  45a1a69

Commits on May 23, 2024

• [Kernel] Initial Activation Quantization Support (vllm-project#4525)

  Show description for a124232
  

  3 peopleauthored
  a124232

Commits on May 16, 2024

• [Kernel] Add w8a8 CUTLASS kernels (vllm-project#4749)

  tlrmchlsmth

  authored
  2060e93

• Add GPTQ Marlin 2:4 sparse structured support (vllm-project#4790)

  Show description for 6979ade
  

  alexm-neuralmagic

  and

  robertgshaw2-neuralmagic

  authored
  6979ade

Commits on May 10, 2024

• [Kernel] Refactor FP8 kv-cache with NVIDIA float8_e4m3 support (vllm-project#4535)

  comaniac

  authored
  c833101

Commits on May 9, 2024

• [ROCm] Add support for Punica kernels on AMD GPUs (vllm-project#3140)

  Show description for ff5abcd
  

  kliuae

  and

  big-yellow-duck

  authored
  ff5abcd

Commits on Apr 30, 2024

• [Misc] Upgrade to torch==2.3.0 (vllm-project#4454)

  mgoin

  authored
  d627a3d

Pagination

PreviousNext