Commits

Branch selector

 main

User selector

dsikka

Datepicker

All time

Commit History

Commits on Sep 13, 2024

• [BugFix] fix group_topk (vllm-project#8430)

  dsikka

  authored
  8f44a92

  Copy full SHA for 8f44a92

Commits on Sep 10, 2024

• [Misc] Fused MoE Marlin support for GPTQ (vllm-project#8217)

  dsikka

  authored
  6cd5e5b

  Copy full SHA for 6cd5e5b

Commits on Sep 6, 2024

• [Misc] Remove SqueezeLLM (vllm-project#8220)

  dsikka

  authored
  23f3222

  Copy full SHA for 23f3222

Commits on Sep 4, 2024

• [Misc] Update fbgemmfp8 to use vLLMParameters (vllm-project#7972)

  Show description for e16fa99
  

  dsikka

  and

  mgoin

  authored
  e16fa99

  Copy full SHA for e16fa99

Commits on Sep 3, 2024

• [Misc] Update GPTQ to use vLLMParameters (vllm-project#7976)

  dsikka

  authored
  2188a60

  Copy full SHA for 2188a60

Commits on Aug 29, 2024

• [misc] update tpu int8 to use new vLLM Parameters (vllm-project#7973)

  dsikka

  authored
  86a677d

  Copy full SHA for 86a677d

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

  Copy full SHA for fc91188

• [Misc] Update compressed tensors lifecycle to remove prefix from create_weights (vllm-project#7825)

  dsikka

  authored
  015e6cc

  Copy full SHA for 015e6cc

Commits on Aug 26, 2024

• [Misc] Update gptq_marlin_24 to use vLLMParameters (vllm-project#7762)

  Show description for dd9857f
  

  dsikka

  and

  mgoin

  authored
  dd9857f

  Copy full SHA for dd9857f

• [Misc] Update qqq to use vLLMParameters (vllm-project#7805)

  dsikka

  authored
  6653040

  Copy full SHA for 6653040

Commits on Aug 23, 2024

• [Misc] Update marlin to use vLLMParameters (vllm-project#7803)

  dsikka

  authored
  f1df5db

  Copy full SHA for f1df5db

Commits on Aug 22, 2024

• [Misc] update fp8 to use vLLMParameter (vllm-project#7437)

  dsikka

  authored
  955b519

  Copy full SHA for 955b519

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

  Copy full SHA for 8678a69

Commits on Aug 13, 2024

• [Misc] Update awq and awq_marlin to use vLLMParameters (vllm-project#7422)

  dsikka

  authored
  b1e5afc

  Copy full SHA for b1e5afc

• [Misc] Update Fused MoE weight loading (vllm-project#7334)

  dsikka

  authored
  d3bdfd3

  Copy full SHA for d3bdfd3

• [Misc] Update gptq_marlin to use new vLLMParameters (vllm-project#7281)

  dsikka

  authored
  fb377d7

  Copy full SHA for fb377d7

• [Misc] Update LM Eval Tolerance (vllm-project#7473)

  dsikka

  authored
  181abbc

  Copy full SHA for 181abbc

Commits on Aug 9, 2024

• [Bugfix] Fix PerTensorScaleParameter weight loading for fused models (vllm-project#7376)

  dsikka

  authored
  5c6c54d

  Copy full SHA for 5c6c54d

Commits on Aug 7, 2024

• [Misc] Refactor linear layer weight loading; introduce BasevLLMParameter and weight_loader_v2 (vllm-project#5874)

  dsikka

  authored
  0f7052b

  Copy full SHA for 0f7052b

Commits on Aug 6, 2024

• [BugFix] Fix DeepSeek remote code (vllm-project#7178)

  dsikka

  authored
  a3bbbfa

  Copy full SHA for a3bbbfa

Commits on Jun 30, 2024

• [Misc] Fix get_min_capability (vllm-project#5971)

  dsikka

  authored
  7836fdc

  Copy full SHA for 7836fdc

Commits on Jun 25, 2024

• [Misc] Update w4a16 compressed-tensors support to include w8a16 (vllm-project#5794)

  dsikka

  authored
  dd248f7

  Copy full SHA for dd248f7

Commits on Jun 19, 2024

• [Misc] Add per channel support for static activation quantization; update w8a8 schemes to share base classes (vllm-project#5650)

  dsikka

  authored
  4a30d7e

  Copy full SHA for 4a30d7e

Commits on Jun 18, 2024

• [Misc] Add channel-wise quantization support for w8a8 dynamic per token activation quantization (vllm-project#5542)

  dsikka

  authored
  95db455

  Copy full SHA for 95db455

Commits on Jun 17, 2024

• [Kernel] compressed-tensors marlin 24 support (vllm-project#5435)

  dsikka

  authored
  890d8d9

  Copy full SHA for 890d8d9

Commits on Jun 13, 2024

• [Kernel] w4a16 support for compressed-tensors (vllm-project#5385)

  Show description for c2637a6
  

  dsikka

  and

  robertgshaw2-redhat

  authored
  c2637a6

  Copy full SHA for c2637a6

Commits on Jun 10, 2024

• [Misc] Update to comply with the new compressed-tensors config (vllm-project#5350)

  Show description for 5884c2b
  

  dsikka

  and

  mgoin

  authored
  5884c2b

  Copy full SHA for 5884c2b

Commits on Jun 7, 2024

• [Kernel] Dynamic Per-Token Activation Quantization (vllm-project#5037)

  Show description for ca3ea51
  

  3 peopleauthored
  ca3ea51

  Copy full SHA for ca3ea51

Commits on May 23, 2024

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

  Show description for a124232
  

  3 peopleauthored
  a124232

  Copy full SHA for a124232