Commits

Branch selector

 9e99407

User selector

All users

Datepicker

All time

Commit History

Commits on Sep 19, 2024

• Create SECURITY.md (vllm-project#8642)

  simon-mo

  authored
  9e99407

  Copy full SHA for 9e99407

• [Doc] Add documentation for GGUF quantization (vllm-project#8618)

  Isotr0py

  authored
  ea4647b

  Copy full SHA for ea4647b

• [Core] simplify logits resort in _apply_top_k_top_p (vllm-project#8619)

  hidva

  authored
  e42c634

  Copy full SHA for e42c634

• [Kernel][Amd] Add fp8 kv cache support for rocm custom paged attention (vllm-project#8577)

  charlifu

  authored
  9cc373f

  Copy full SHA for 9cc373f

• [Frontend] Use MQLLMEngine for embeddings models too (vllm-project#8584)

  njhill

  authored
  76515f3

  Copy full SHA for 76515f3

• [MISC] remove engine_use_ray in benchmark_throughput.py (vllm-project#8615)

  jikunshang

  authored
  855c8ae

  Copy full SHA for 855c8ae

• [Bugfix] fixing sonnet benchmark bug in benchmark_serving.py (vllm-project#8616)

  KuntaiDu

  authored
  c52ec5f

  Copy full SHA for c52ec5f

• Revert "[Misc][Bugfix] Disable guided decoding for mistral tokenizer" (vllm-project#8593)

  ywang96

  authored
  02c9afa

  Copy full SHA for 02c9afa

• [Bugfix] [Encoder-Decoder] Bugfix for encoder specific metadata construction during decode of encoder-decoder models. (vllm-project#8545)

  sroy745

  authored
  3118f63

  Copy full SHA for 3118f63

• [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

• [Bugfix] add dead_error property to engine client (vllm-project#8574)

  Show description for 0d47bf3
  joerunde

  authored
  0d47bf3

  Copy full SHA for 0d47bf3

• [BugFix] Nonzero exit code if MQLLMEngine startup fails (vllm-project#8572)

  njhill

  authored
  d9cd78e

  Copy full SHA for d9cd78e

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

  tlrmchlsmth

  authored
  db9120c

  Copy full SHA for db9120c

• [AMD][ROCm]Quantization methods on ROCm; Fix _scaled_mm call (vllm-project#8380)

  Show description for b3195bc
  

  3 peopleauthored
  b3195bc

  Copy full SHA for b3195bc

• [Model] Support Solar Model (vllm-project#8386)

  Show description for e18749f
  

  shing100

  and

  mgoin

  authored
  e18749f

  Copy full SHA for e18749f

• [Core] zmq: bind only to 127.0.0.1 for local-only usage (vllm-project#8543)

  Show description for d65798f
  russellb

  authored
  d65798f

  Copy full SHA for d65798f

• [Core] *Prompt* logprobs support in Multi-step (vllm-project#8199)

  afeldman-nm

  authored
  a8c1d16

  Copy full SHA for a8c1d16

• [Core][Bugfix][Perf] Introduce MQLLMEngine to avoid asyncio OH (vllm-project#8157)

  Show description for 7c7714d
  

  4 peopleauthored
  7c7714d

  Copy full SHA for 7c7714d

• [CI/Build] Update Ruff version (vllm-project#8469)

  Show description for 9d104b5
  

  aarnphm

  and

  DarkLight1337

  authored
  9d104b5

  Copy full SHA for 9d104b5

• [CI/Build] Avoid CUDA initialization (vllm-project#8534)

  DarkLight1337

  authored
  6ffa3f3

  Copy full SHA for 6ffa3f3

• [Misc] Add argument to disable FastAPI docs (vllm-project#8554)

  Jeffwan

  authored
  e351572

  Copy full SHA for e351572

• [CI/Build] fix Dockerfile.cpu on podman (vllm-project#8540)

  dtrifiro

  authored
  95965d3

  Copy full SHA for 95965d3

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

• [CI/Build] Excluding kernels/test_gguf.py from ROCm (vllm-project#8520)

  alexeykondrat

  authored
  09deb47

  Copy full SHA for 09deb47

• [doc] improve installation doc (vllm-project#8550)

  Show description for fa0c114
  

  youkaichao

  and

  Imss27

  authored
  fa0c114

  Copy full SHA for fa0c114

• [Bugfix] Fix TP > 1 for new granite (vllm-project#8544)

  Show description for 98f9713
  joerunde

  authored
  98f9713

  Copy full SHA for 98f9713

• [Misc] Don't dump contents of kvcache tensors on errors (vllm-project#8527)

  njhill

  authored
  56c3de0

  Copy full SHA for 56c3de0

• [Model] Add mistral function calling format to all models loaded with "mistral" format (vllm-project#8515)

  Show description for a54ed80
  

  patrickvonplaten

  and

  DarkLight1337

  authored
  a54ed80

  Copy full SHA for a54ed80

• [Feature][kernel] tensor parallelism with bitsandbytes quantization (vllm-project#8434)

  chenqianfzh

  authored
  9855b99

  Copy full SHA for 9855b99

• [Encoder decoder] Add cuda graph support during decoding for encoder-decoder models (vllm-project#7631)

  sroy745

  authored
  1009e93

  Copy full SHA for 1009e93

• [Benchmark] Support sample from HF datasets and image input for benchmark_serving (vllm-project#8495)

  Isotr0py

  authored
  1b6de83

  Copy full SHA for 1b6de83

• [Misc] Limit to ray[adag] 2.35 to avoid backward incompatible change (vllm-project#8509)

  Show description for cbdb252
  ruisearch42

  authored
  cbdb252

  Copy full SHA for cbdb252

• [torch.compile] register allreduce operations as custom ops (vllm-project#8526)

  youkaichao

  authored
  99aa4ed

  Copy full SHA for 99aa4ed

• [Misc][Bugfix] Disable guided decoding for mistral tokenizer (vllm-project#8521)

  ywang96

  authored
  ee2bcea

  Copy full SHA for ee2bcea

• [Frontend] Improve Nullable kv Arg Parsing (vllm-project#8525)

  Show description for 1c1bb38
  alex-jw-brooks

  authored
  1c1bb38

  Copy full SHA for 1c1bb38

Pagination

Previous

Next