Commits

Breadcrumbs

History for

onbinary-wheels

User selector

All users

All time

Commit History

Commits on Apr 1, 2024

• feat: add support for KV cache quantization options (#1307)

  Show description for f165048
  

  Limour-dev

  and

  abetlen

  authored
  f165048

  Copy full SHA for f165048

Commits on Mar 31, 2024

• feat: Add logprobs support to chat completions (#1311)

  Show description for aa9f1ae
  

  windspirit95

  and

  abetlen

  authored
  aa9f1ae

  Copy full SHA for aa9f1ae

Commits on Mar 23, 2024

• fix(server): minor type fixes

  abetlen

  committed
  d11ccc3

  Copy full SHA for d11ccc3

Commits on Mar 19, 2024

• docs: Add chat examples to openapi ui

  abetlen

  committed
  f7decc9

  Copy full SHA for f7decc9

Commits on Mar 9, 2024

• feat: Add endpoints for tokenize, detokenize and count tokens (#1136)

  Show description for c139f8b
  

  felipelo

  and

  abetlen

  authored
  c139f8b

  Copy full SHA for c139f8b

Commits on Feb 28, 2024

• misc: Format

  abetlen

  committed
  727d60c

  Copy full SHA for 727d60c

• feat: Update llama.cpp

  abetlen

  committed
  0d37ce5

  Copy full SHA for 0d37ce5

Commits on Feb 26, 2024

• feat(server): Add support for pulling models from Huggingface Hub (#1222)

  Show description for 4d574bd
  abetlen

  authored
  4d574bd

  Copy full SHA for 4d574bd

• fix: remove prematurely commited change

  abetlen

  committed
  dcf38f6

  Copy full SHA for dcf38f6

Commits on Feb 25, 2024

• feat: Update llama.cpp

  abetlen

  committed
  2292af5

  Copy full SHA for 2292af5

Commits on Feb 17, 2024

• feat: Update llama.cpp

  abetlen

  committed
  fdce078

  Copy full SHA for fdce078

Commits on Feb 15, 2024

• fix: Use '\n' seperator for EventSourceResponse (#1188)

  Show description for ea1f88d
  

  khimaros

  and

  abetlen

  authored
  ea1f88d

  Copy full SHA for ea1f88d

Commits on Feb 8, 2024

• fix: broken import

  abetlen

  committed
  85d3374

  Copy full SHA for 85d3374

• feat: Integrate functionary v1.4 and v2 models + add custom tokenizer support to Llama class (#1078)

  Show description for 9018270
  

  jeffrey-fong

  and

  abetlen

  authored
  9018270

  Copy full SHA for 9018270

Commits on Jan 31, 2024

• Add speculative decoding (#1120)

  Show description for fb762a6
  abetlen

  authored
  fb762a6

  Copy full SHA for fb762a6

Commits on Jan 29, 2024

• Automatically set chat format from gguf (#1110)

  Show description for da003d8
  abetlen

  authored
  da003d8

  Copy full SHA for da003d8

Commits on Jan 25, 2024

• feat(server): include llama-cpp-python version in openapi spec

  abetlen

  committed
  cde7514

  Copy full SHA for cde7514

Commits on Jan 21, 2024

• fix: pass chat handler not chat formatter for huggingface autotokenizer and tokenizer_config formats.

  abetlen

  committed
  24f3945

  Copy full SHA for 24f3945

Commits on Jan 19, 2024

• Fix python3.8 support

  abetlen

  committed
  141293a

  Copy full SHA for 141293a

• feat: Add ability to load chat format from huggingface autotokenizer or tokenizer_config.json files.

  abetlen

  committed
  b8fc1c7

  Copy full SHA for b8fc1c7

Commits on Jan 18, 2024

• Offload KQV by default

  abetlen

  committed
  48c3b77

  Copy full SHA for 48c3b77

Commits on Jan 16, 2024

• fix(cli): allow passing n_ctx=0 to openAI API server args to use model n_ctx_train field per #1015 (#1093)

  K-Mistele

  authored
  9c36688

  Copy full SHA for 9c36688

• Support Accept text/event-stream in chat and completion endpoints, resolves #1083 (#1088)

  Show description for cfb7da9
  

  3 peopleauthored
  cfb7da9

  Copy full SHA for cfb7da9

Commits on Jan 15, 2024

• Add split_mode option. Closes #1085

  abetlen

  committed
  84615ad

  Copy full SHA for 84615ad

• Implement GGUF metadata KV overrides (#1011)

  Show description for 76aafa6
  

  phiharri

  and

  abetlen

  authored
  76aafa6

  Copy full SHA for 76aafa6

Commits on Dec 22, 2023

• docs: add server config docs

  abetlen

  committed
  522aecb

  Copy full SHA for 522aecb

• server: Support none defaulting to infinity for completions (#111)

  Show description for 4b01a87
  

  swg

  and

  abetlen

  authored
  4b01a87

  Copy full SHA for 4b01a87

• [Feat] Multi model support (#931)

  Show description for 12b7f2f
  

  D4ve-R

  and

  abetlen

  authored
  12b7f2f

  Copy full SHA for 12b7f2f

Commits on Dec 21, 2023

• Implement openai api compatible authentication (#1010)

  docmeth02

  authored
  33cc623

  Copy full SHA for 33cc623

Commits on Dec 18, 2023

• Add offload_kqv option to llama and server

  abetlen

  committed
  095c650

  Copy full SHA for 095c650

• Bugfix: Remove f16_kv, add offload_kqv field (#1019)

  Show description for 62944df
  brandonrobertz

  authored
  62944df

  Copy full SHA for 62944df

Commits on Dec 12, 2023

• Add support for running the server with SSL (#994)

  rgerganov

  authored
  8e44a32

  Copy full SHA for 8e44a32

Commits on Nov 24, 2023

• docs: Update openapi endpoint names

  abetlen

  committed
  1a7bf20

  Copy full SHA for 1a7bf20

Commits on Nov 21, 2023

• Fix #569

  abetlen

  committed
  128dc47

  Copy full SHA for 128dc47

• Format

  abetlen

  committed
  7a3f878

  Copy full SHA for 7a3f878