Commit Graph
100 Commits
Author SHA1 Message Date
Sigbjørn SkjæretandGitHub 764f1e64a1 graph : ensure DS32 kq_mask_lid is F32 (#23864) 2026-05-29 19:55:14 +02:00
Sigbjørn SkjæretandGitHub 3ef2369551 ci : run ui publish on ubuntu-slim (#23818)
* run ui publish on self-hosted fast

* run on ubuntu-slim
2026-05-28 20:58:32 +03:00
Sigbjørn SkjæretandGitHub 87b0a60cdd pyproject : add conversion folder and update dependencies (#23746)
* add conversion folder and update dependencies

* limit python version for triton

* update dev-dependencies section
2026-05-27 15:06:18 +02:00
Sigbjørn SkjæretandGitHub 2d0656fbdd ci : bump cuda release to 13.3 (#23749) 2026-05-27 15:06:08 +03:00
Sigbjørn SkjæretandGitHub b3a739c9b6 ci : remove wasm test (#23733)
* run tests in correct build folder

* remove wasm test
2026-05-27 13:11:37 +03:00
Sigbjørn SkjæretandGitHub 062d3115aa ci : fix pre-tokenizer-hashes check (#23651) 2026-05-25 10:41:25 +02:00
Sigbjørn SkjæretandGitHub 5d246a792d convert : minor fixes for numpy 2.x (#23571) 2026-05-24 09:51:31 +02:00
Sigbjørn SkjæretandGitHub 7e50ef7d79 docker : copy conversion files (#23370) 2026-05-20 11:03:18 +02:00
Sigbjørn SkjæretandGitHub b7393a4d19 convert : update mtp related help (#23334)
* update mtp related help

* remove outdated experimental text
2026-05-19 21:16:58 +02:00
Sigbjørn SkjæretandGitHub 4b262ab662 ci : install libssl-dev (#23325) 2026-05-19 11:11:04 +03:00
Sigbjørn SkjæretandGitHub 00c461ce1a ci : install server kleidiai runner dependencies (#23259) 2026-05-19 09:06:56 +02:00
Sigbjørn SkjæretandGitHub f1c1c5c057 convert : filter lora tensor names (#23077) 2026-05-19 09:44:25 +03:00
Sigbjørn SkjæretandGitHub 77e38d68f2 add myself to conversion (#23261) 2026-05-18 12:42:56 +02:00
Sigbjørn SkjæretandGitHub dd7cad7197 cmake : do not check for bin install dir (#23234) 2026-05-18 02:33:14 +02:00
Sigbjørn SkjæretandGitHub e0de4c2419 cmake : do not install conversion script (#23204) 2026-05-17 18:07:21 +02:00
Sigbjørn SkjæretandGitHub 49d1701bd2 ci : fix release symlinks (#23119) 2026-05-16 01:09:28 +02:00
Sigbjørn SkjæretandGitHub 18d1717d62 convert : fix Qwen3 ASR conversion (#23081)
* fix qwen3asr

* fix qwen3asr
2026-05-15 18:38:39 +02:00
Sigbjørn SkjæretandGitHub 769cc93a43 ci : fix transform of top . entry in release archive (#23080)
* fix transform of top . entry in release archive

* simplify
2026-05-15 13:13:16 +02:00
Sigbjørn SkjæretandGitHub bcfe63fc53 llama-eval : enable type check (#22988) 2026-05-13 09:14:24 +03:00
Sigbjørn SkjæretandGitHub fa62042af9 ci : bump ty to 0.0.35 (#22961) 2026-05-12 11:34:10 +02:00
Sigbjørn SkjæretandGitHub 5755a100cd model : fix model type check for granite/llama3 and deepseek2/glm4.7 lite (#22870) 2026-05-10 08:44:29 +02:00
Sigbjørn SkjæretandGitHub 74d6248f71 convert : add filter_tensors method to pre-filter tensors (#22597)
* add filter_tensors classmethod

* remove language_model

* fix parts validation
2026-05-06 08:06:05 +02:00
fa595462ca graph : handle non-contiguous Q/K/V in mul_mat_aux (#22630)
* qkv may not always be contiguous

* cont : make the cont conditional

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2026-05-05 06:34:44 +03:00
Sigbjørn SkjæretandGitHub 6118c043b1 ci : bump ty to 0.0.33 (#22535)
* bump ty to 0.0.33

* update typings
2026-04-30 16:15:54 +03:00
Sigbjørn SkjæretandGitHub d13540becd convert : remove input_scale for dequantized fp8 modelopt (#22356) 2026-04-27 08:45:01 +02:00
Sigbjørn SkjæretandGitHub 0c6ee1cade ggml-cpu : re-enable fast gelu_quick_f16 (#22339) 2026-04-26 09:28:14 +03:00
Sigbjørn SkjæretandGitHub 0949beb5a3 fix build number for sycl release (#22283) 2026-04-23 21:38:58 +08:00
Sigbjørn SkjæretandGitHub 037bfe38d0 ci : install spirv-headers for vulkan-cross (#22109) 2026-04-19 10:32:08 +03:00
Sigbjørn SkjæretandGitHub 4f02d47339 model : refactor bias tensor variable names (#22079)
* refactor bias tensor variable names

* use create_tensor_qkv for jina-bert-v2
2026-04-18 20:12:00 +02:00
Sigbjørn SkjæretandGitHub 23b8cc4991 android : libcommon -> libllama-common (#22076) 2026-04-18 11:19:40 +02:00
Sigbjørn SkjæretandGitHub 83d58e02fc ci : free disk space for rocm release (#22012) 2026-04-18 09:37:30 +02:00
Sigbjørn SkjæretandGitHub 89a5474f0e convert : fix (ignore for now) typings errors (#22002) 2026-04-18 09:36:41 +02:00
Sigbjørn SkjæretandGitHub 30dce2cf29 cli : use get_media_marker (#22017) 2026-04-17 00:12:31 +02:00
Sigbjørn SkjæretandGitHub f772f6e434 model : support NVFP4 tensors for Gemma4 (#21971)
* support nvfp4 tensors for Gemma4

* add wo_s to build_attn

* add wo_s to build_attn

* fix glm4
2026-04-16 16:51:47 +02:00
Sigbjørn SkjæretandGitHub 1e9d771e2c convert : force f16 or f32 on step3-vl conv weights (#21646) 2026-04-12 19:22:29 +02:00
Sigbjørn SkjæretandGitHub 2b2cd57de6 ggml : fix a few instances of missing GGML_TYPE_Q1_0 cases (#21716) 2026-04-11 09:45:00 +03:00
Sigbjørn SkjæretandGitHub 941146b3f1 convert : fix block_ff_dim retrieval for lfm2 (#21508) 2026-04-06 14:05:18 +02:00
Sigbjørn SkjæretandGitHub 1f34806c44 jinja: coerce input for string-specific filters (#21370) 2026-04-03 15:03:33 +02:00
Sigbjørn SkjæretandGitHub e2eb39e81c ci : bump ty to 0.0.26 (#21156)
* fix incorrect type ignore comments

* bump ty to 0.0.26
2026-03-30 09:29:15 +02:00
Sigbjørn SkjæretandGitHub 7c203670f8 add missing ROPE_FACTORS_LONG/SHORT for MiniCPM (#21150) 2026-03-29 19:45:40 +02:00
Sigbjørn SkjæretandGitHub 65097181e4 fix **/x glob matching (#21129) 2026-03-28 22:27:38 +01:00
Sigbjørn SkjæretandGitHub 3a14a542f5 common : add character class support to glob_match (#21111)
* add character class support to glob_match

* remove pointless reference
2026-03-28 19:57:37 +01:00
Sigbjørn SkjæretandGitHub c46758d28f cli : add /glob command (#21084)
* add /glob command

* output error when max files reached

* support globbing outside curdir
2026-03-28 02:33:04 +01:00
Sigbjørn SkjæretandGitHub 403c9c9cef ci : bump gguf publish python version (#20982) 2026-03-25 11:04:59 +02:00
Sigbjørn SkjæretandGitHub 8fc85db9d2 ci : limit requirements versions (#20980)
* set requests version

* limit versions outside requirements
2026-03-25 10:55:37 +02:00
Sigbjørn SkjæretandGitHub 23c9182ce8 jinja : refactor token advancement (#20864)
* refactor token advancement

* exercise sub-expressions
2026-03-22 17:45:10 +01:00
Sigbjørn SkjæretandGitHub 29b28a9824 ci : switch from pyright to ty (#20826)
* type fixes

* switch to ty

* tweak rules

* tweak more rules

* more tweaks

* final tweak

* use common import-not-found rule
2026-03-21 08:54:34 +01:00
Sigbjørn SkjæretandGitHub 811397745e vocab : assert array size of scores and toktypes (#20737) 2026-03-19 08:34:04 +01:00
Sigbjørn SkjæretandGitHub d13d60af1d gguf-py : cleaner way to get the first key (#20727) 2026-03-18 23:21:42 +01:00
Sigbjørn SkjæretandGitHub ab0bb93748 ci : bump ccache [no ci] (#20679)
* bump ccache

* forgotten

* disable for s390x

* disable also for ppc64le
2026-03-17 14:54:31 +01:00
Sigbjørn SkjæretandGitHub 55e87026f7 tests : write to binary buffer to avoid newline translation in jinja -py [no ci] (#20365) 2026-03-16 20:40:22 +01:00
Sigbjørn SkjæretandGitHub 0ed992973b ci : update labeler (#20629) 2026-03-16 20:24:20 +01:00
Sigbjørn SkjæretandGitHub de8f01c2d7 model : wire up Nemotron-H tensors for NVFP4 support (#20561)
* wire up Nemotron-H tensors for NVFP4 support

* add ssm tensors

* alignment
2026-03-16 09:19:16 +01:00
Sigbjørn SkjæretandGitHub ebbf544ed1 sycl : fix for untransposed GDA recurrent state (#20583) 2026-03-15 19:10:15 +01:00
Sigbjørn SkjæretandGitHub b91d7dfe5b ci : only save openvino caches on github-hosted master (#20593)
* only save openvino ccache on master

* disable toolkit cache if self-hosted

* only cache on github-hosted runners

* remove toolkit cache [no ci]
2026-03-15 18:58:13 +01:00
Sigbjørn SkjæretandGitHub cf45437d35 codeowners : use teams (#20526)
* use teams

* update

* update

* update

* update

* update
2026-03-15 14:26:10 +01:00
Sigbjørn SkjæretandGitHub 89d0aec042 convert : support contiguous method on lora tensors (#20489) 2026-03-15 12:15:12 +01:00
Sigbjørn SkjæretandGitHub c3e3f9e533 convert : better mtp check and fix return [no ci] (#20419) 2026-03-12 10:04:20 +01:00
Sigbjørn SkjæretandGitHub f90bd1dd84 llama : whitespace cleanup (#20422) 2026-03-11 21:18:29 +01:00
Sigbjørn SkjæretandGitHub ec947d2b16 common : fix incorrect uses of stoul (#20313) 2026-03-10 11:40:26 +01:00
Sigbjørn SkjæretandGitHub 35bee031e1 graph : remove redundant scale_w parameter (#20235) 2026-03-08 18:58:28 +01:00
Sigbjørn SkjæretandGitHub b5ed0e058c cli : add command and file auto-completion (#19985) 2026-03-05 10:47:28 +01:00
Sigbjørn SkjæretandGitHub cf232515c9 convert : register Qwen 3.5 ForCausalLM for text only (#20119) 2026-03-05 10:30:02 +01:00
Sigbjørn SkjæretandGitHub d969e933e1 tools : add missing clocale include in mtmd-cli [no ci] (#20107) 2026-03-04 14:18:04 +01:00
Sigbjørn SkjæretandGitHub e8e261699a cli : provide model with text filename (#19783) 2026-02-22 22:33:49 +01:00
Sigbjørn SkjæretandGitHub 9f0684f003 ci : fix rocm archive name [no ci] (#19808) 2026-02-22 16:14:37 +01:00
Sigbjørn SkjæretandGitHub e877ad8bd9 ci : fix rocm release path [no ci] (#19784) 2026-02-22 08:07:46 +01:00
Sigbjørn SkjæretandGitHub e48349a49d ci : bump komac version (#19682) 2026-02-17 09:30:31 +01:00
Sigbjørn SkjæretandGitHub 079feab9e3 convert : ensure all models handle new experts count (#19621)
* ensure all models handle new experts count

* revert removal for PhiMoeModel, does not inherit from base
2026-02-14 22:22:32 +01:00
Sigbjørn SkjæretandGitHub 0d00ef65ed convert : store ffn_gate_inp_shexp as F32 (#19606) 2026-02-14 08:17:43 +01:00
Sigbjørn SkjæretandGitHub b2ecc0cdb4 support --verbose-prompt (#19576) 2026-02-13 12:49:10 +01:00
Sigbjørn SkjæretandGitHub 9a5f57795c ci : remove server job from webui and move slow test (#19424)
* remove server job from webui and move slow test

* use pip-install option
2026-02-08 01:20:00 +01:00
Sigbjørn SkjæretandGitHub b828e18c75 docker : fix vulkan build (#19352) 2026-02-05 11:10:39 +01:00
Sigbjørn SkjæretandGitHub 11fb327bf3 vendor : add missing llama_add_compile_flags (#19322)
* add missing llama_add_compile_flags

* disable all warnings for ssl, crypto and fipsmodule
2026-02-05 02:27:38 +01:00
Sigbjørn SkjæretandGitHub a6fd8ca1fe models : remove unnecessary cont in openelm (#19289) 2026-02-03 14:20:57 +01:00
Sigbjørn SkjæretandGitHub b45ef2702c jinja : do not pass empty tools and add some none filters (#19176) 2026-01-29 14:06:54 +01:00
Sigbjørn SkjæretandGitHub 50e8962f79 ci : find latest release with asset for winget (#19161) 2026-01-28 22:05:39 +01:00
Sigbjørn SkjæretandGitHub 60368e1d73 jinja : undefined should be treated as sequence/iterable (return string/array) by filters/tests (#19147)
* undefined is treated as iterable (string/array) by filters

`tojson` is not a supported `undefined` filter

* add tests

* add sequence and iterable tests

keep it DRY and fix some types
2026-01-28 14:40:29 +01:00
2b4cbd2834 jinja : implement mixed type object keys (#18955)
* implement mixed type object keys

* add tests

* refactor

* minor fixes

* massive refactor

* add more tests

* forgotten tuples

* fix array/object is_hashable

* correct (albeit broken) jinja responses

verified with transformers

* improved hashing and equality

* refactor hash function

* more exhausive test case

* clean up

* cont

* cont (2)

* missing cstring

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
2026-01-27 19:50:42 +01:00
Sigbjørn SkjæretandGitHub c0204a0893 ci : revert slim runner for winget (#19129) 2026-01-27 11:54:25 +01:00
Sigbjørn SkjæretandGitHub 142cbe2ac6 ci : use new 1vCPU runner for lightweight jobs (#19107)
* use new 1vCPU runner for lightweight jobs

* pyright is too heavy, look into ty some day

use new pip-install input
2026-01-26 15:22:49 +01:00
Sigbjørn SkjæretandGitHub 0bf5636938 convert : yield Gemma3N custom_map tensors directly (#19091) 2026-01-25 18:03:34 +01:00
Sigbjørn SkjæretandGitHub 70d860824a convert : fix Gemma3N, GraniteMoe and Ernie4.5Moe (#19084)
* fix Gemma3N and Ernie4.5Moe

* fix GraniteMoe
2026-01-25 13:05:05 +01:00
Sigbjørn SkjæretandGitHub 959ecf7f23 jinja : fix undefined keys and attributes and int/float as bool (#18924)
* fix undefined keys and attributes

* add falsy tests

* as_bool for integers and floats

* more falsy/truthy tests

* --typo
2026-01-19 20:29:43 +01:00
Sigbjørn SkjæretandGitHub 4037093c66 ci : run test-jinja -py on high perf [no ci] (#18916) 2026-01-19 20:29:15 +01:00
Sigbjørn SkjæretandGitHub bbcdac0189 jinja : fix object item order (and properly implement dictsort) (#18904)
* fix object item order

* as_ordered_object

* copy whole object
2026-01-18 03:40:06 +01:00
Sigbjørn SkjæretandGitHub d03c45c9c5 jinja : attribute support for join, map and sort (#18883)
* support negative array index and default value

* attribute support (int and str) for join, map and sort

* add tests

* update CODEOWNERS

* improve fixme sorting comment
2026-01-18 02:53:01 +01:00
Sigbjørn SkjæretandGitHub 10c98cbdf6 jinja : add missing tojson filter for bool (#18900)
* add missing tojson for bool

* add more literal tests
2026-01-18 01:05:09 +01:00
Sigbjørn SkjæretandGitHub 420960ab92 jinja : fix lexing of float literals with sign (#18901)
* fix lexing of float literals with sign

* add test

* consume_numeric
2026-01-18 00:57:51 +01:00
Sigbjørn SkjæretandGitHub 57c0beaed0 ci : add label for jinja changes (#18903) 2026-01-17 21:52:02 +01:00
Sigbjørn SkjæretandGitHub 2a13180100 model-loader : support bool array sliding window pattern (#18850) 2026-01-15 10:12:46 +01:00
Sigbjørn SkjæretandGitHub 7fdc8c893d scripts : follow api redirects in pr2wt.sh (#18739) 2026-01-10 16:04:05 +01:00
Sigbjørn SkjæretandGitHub 5b8844ae53 scripts : fix repos cloned with .git extension (#18669) 2026-01-07 22:35:34 +01:00
Sigbjørn SkjæretandGitHub 7e16fef085 convert : more variants of rope_theta config entries (#18668) 2026-01-07 22:34:51 +01:00
Sigbjørn SkjæretandGitHub 9dfa8ee950 ci : run cann build unconditionally [no ci] (#18659) 2026-01-07 13:07:08 +01:00
Sigbjørn SkjæretandGitHub eadc4184ca llama : refactor rope_freq_base/scale_swa conversion and init (#18553)
* refactor rope_freq_base/scale_swa conversion and init

* safe defaults for unknowns

* update relevant models

* grammar

* add get_rope_freq_scale to modern-bert

* const

* const

* log swa info
2026-01-05 09:14:04 +01:00
Sigbjørn SkjæretandGitHub 169ee68ffb model : remove modern-bert iswa template (#18529)
* remove modern-bert iswa template

* forgotten
2026-01-02 00:06:42 +01:00
Sigbjørn SkjæretandGitHub 0db8109849 convert : lint fix (#18507) 2025-12-31 14:28:21 +01:00
Sigbjørn SkjæretandGitHub 4849661d98 docker : add CUDA 13.1 image build (#18441)
* add updated cuda-new.Dockerfile for Ubuntu 24.04 compatibilty

* add cuda13 build
2025-12-30 22:28:53 +01:00
Sigbjørn SkjæretandGitHub 74e05131e9 ci : remove non-windows zip artifacts (#18201)
* remove non-windows zip artifacts

* add cuda dll links
2025-12-19 22:29:46 +01:00