Commits

Branch selector

 main

User selector

tlrmchlsmth

Datepicker

All time

Commit History

Commits on Nov 27, 2024

• [Kernel] Remove if-else with identical branches in marlin 2:4 (vllm-project#10687)

  Show description for e225110
  tlrmchlsmth

  authored
  e225110

  Copy full SHA for e225110

Commits on Nov 23, 2024

• [Misc] Add pynccl wrappers for all_gather and reduce_scatter (vllm-project#9432)

  tlrmchlsmth

  authored
  978b397

  Copy full SHA for 978b397

Commits on Nov 15, 2024

• [Misc] Change RedundantReshapesPass and FusionPass logging from info to debug (vllm-project#10308)

  Show description for 2885ba0
  tlrmchlsmth

  authored
  2885ba0

  Copy full SHA for 2885ba0

Commits on Nov 5, 2024

• [Bugfix] Fixup Mamba (vllm-project#10004)

  Show description for ad23318
  tlrmchlsmth

  authored
  ad23318

  Copy full SHA for ad23318

• [Core] Use os.sched_yield in ShmRingBuffer instead of time.sleep (vllm-project#9994)

  Show description for 04bbf38
  tlrmchlsmth

  authored
  04bbf38

  Copy full SHA for 04bbf38

Commits on Oct 23, 2024

• [Bugfix] Fix divide by zero when serving Mamba models (vllm-project#9617)

  Show description for e5ac6a4
  tlrmchlsmth

  authored
  e5ac6a4

  Copy full SHA for e5ac6a4

Commits on Oct 18, 2024

• [Bugfix] Fix offline_inference_with_prefix.py (vllm-project#9505)

  tlrmchlsmth

  authored
  ae8b633

  Copy full SHA for ae8b633

Commits on Oct 16, 2024

• [Bugfix][Kernel] Prevent integer overflow in fp8 dynamic per-token quantize kernel (vllm-project#9425)

  tlrmchlsmth

  authored
  c3fab5f

  Copy full SHA for c3fab5f

Commits on Oct 15, 2024

• [Bugfix] Clean up some cruft in mamba.py (vllm-project#9343)

  tlrmchlsmth

  authored
  169b530

  Copy full SHA for 169b530

Commits on Oct 13, 2024

• [Bugfix] Bandaid fix for speculative decoding tests (vllm-project#9327)

  tlrmchlsmth

  authored
  16b24e7

  Copy full SHA for 16b24e7

Commits on Oct 11, 2024

• [Model] Support Mamba (vllm-project#6484)

  tlrmchlsmth

  authored
  7342a7d

  Copy full SHA for 7342a7d

Commits on Sep 29, 2024

• [Build/CI] Set FETCHCONTENT_BASE_DIR to one location for better caching (vllm-project#8930)

  tlrmchlsmth

  authored
  2e7fe7e

  Copy full SHA for 2e7fe7e

Commits on Sep 26, 2024

• [Bugfix] Fixup advance_step.cu warning (vllm-project#8815)

  tlrmchlsmth

  authored
  71d21c7

  Copy full SHA for 71d21c7

• [Bugfix] Fix print_warning_once's line info (vllm-project#8867)

  tlrmchlsmth

  authored
  e2f6f26

  Copy full SHA for e2f6f26

• [Build/CI] Upgrade to gcc 10 in the base build Docker image (vllm-project#8814)

  tlrmchlsmth

  authored
  f70bcca

  Copy full SHA for f70bcca

Commits on Sep 23, 2024

• [Bugfix] Avoid some bogus messages RE CUTLASS's revision when building (vllm-project#8702)

  tlrmchlsmth

  authored
  3dda7c2

  Copy full SHA for 3dda7c2

Commits on Sep 21, 2024

• [Kernel][Bugfix] Delete some more useless code in marlin_moe_ops.cu (vllm-project#8643)

  tlrmchlsmth

  authored
  d66ac62

  Copy full SHA for d66ac62

Commits on Sep 19, 2024

• [Kernel] Remove marlin moe templating on thread_m_blocks (vllm-project#8573)

  Show description for 4c34ce8
  tlrmchlsmth

  authored
  4c34ce8

  Copy full SHA for 4c34ce8

Commits on Sep 18, 2024

• [Kernel] Change interface to Mamba selective_state_update for continuous batching (vllm-project#8039)

  tlrmchlsmth

  authored
  db9120c

  Copy full SHA for db9120c

Commits on Sep 17, 2024

• [Kernel] Change interface to Mamba causal_conv1d_update for continuous batching (vllm-project#8012)

  tlrmchlsmth

  authored
  8110e44

  Copy full SHA for 8110e44

Commits on Sep 10, 2024

• [CI/Build][Kernel] Update CUTLASS to 3.5.1 tag (vllm-project#8043)

  tlrmchlsmth

  authored
  94144e7

  Copy full SHA for 94144e7

Commits on Aug 5, 2024

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

  tlrmchlsmth

  authored
  4cf1dc3

  Copy full SHA for 4cf1dc3

• [CI/Build] Suppress divide-by-zero and missing return statement warnings (vllm-project#7001)

  tlrmchlsmth

  authored
  6e4852c

  Copy full SHA for 6e4852c

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

  tlrmchlsmth

  authored
  8571ac4

  Copy full SHA for 8571ac4

Commits on Aug 1, 2024

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

  tlrmchlsmth

  authored
  6a11fdf

  Copy full SHA for 6a11fdf

Commits on Jul 30, 2024

• [Kernel] Remove scaled_fp8_quant kernel padding footgun (vllm-project#6842)

  tlrmchlsmth

  authored
  d7a299e

  Copy full SHA for d7a299e

• [Kernel] Squash a few more warnings (vllm-project#6914)

  tlrmchlsmth

  authored
  cbbc904

  Copy full SHA for cbbc904

• [Kernel] Fix marlin divide-by-zero warnings (vllm-project#6904)

  tlrmchlsmth

  authored
  61a97c3

  Copy full SHA for 61a97c3

• [Kernel] Remove unused variables in awq/gemm_kernels.cu (vllm-project#6908)

  tlrmchlsmth

  authored
  aae6d36

  Copy full SHA for aae6d36

Commits on Jul 29, 2024

• [Kernel] Fix deprecation function warnings squeezellm quant_cuda_kernel (vllm-project#6901)

  tlrmchlsmth

  authored
  60d1c6e

  Copy full SHA for 60d1c6e

Commits on Jul 26, 2024

• [Bugfix][Kernel] Promote another index to int64_t (vllm-project#6838)

  tlrmchlsmth

  authored
  50704f5

  Copy full SHA for 50704f5

Commits on Jul 25, 2024

• [Bugfix] Add synchronize to prevent possible data race (vllm-project#6788)

  Show description for 95db75d
  

  tlrmchlsmth

  and

  LucasWilkinson

  authored
  95db75d

  Copy full SHA for 95db75d

Commits on Jul 22, 2024

• [Bugfix][Kernel] Use int64_t for indices in fp8 quant kernels (vllm-project#6649)

  tlrmchlsmth

  authored
  fea59c7

  Copy full SHA for fea59c7

Commits on Jul 19, 2024

• [CI/Build] Build on Ubuntu 20.04 instead of 22.04 (vllm-project#6517)

  tlrmchlsmth

  authored
  1689219

  Copy full SHA for 1689219

Commits on Jul 18, 2024

• [Kernel] Implement fallback for FP8 channelwise using torch._scaled_mm (vllm-project#6552)

  tlrmchlsmth

  authored
  4ffffcc

  Copy full SHA for 4ffffcc

Pagination

Previous

Next