f0564f9caf
updated lite, added better separators for multimodal chunks (universal)
2025-07-17 00:11:08 +08:00
2a59adce0f
stay on macos 14
2025-07-16 15:47:33 +08:00
cbe9fc87c5
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# src/llama-vocab.cpp
2025-07-16 12:03:54 +08:00
c81f4192f9
gguf-py : dump bpw per layer and model in markdown mode ( #14703 )
Python check requirements.txt / check-requirements (push) Failing after 12s
Python Type-Check / pyright type-check (push) Successful in 56s
2025-07-16 00:04:42 +02:00
4a4f426944
model : add Kimi-K2 support ( #14654 )
...
* Kimi-K2 conversion
* add Kimi_K2 pre type
* Kimi-K2
* Kimi-K2 unicode
* Kimi-K2
* LLAMA_MAX_EXPERTS 384
* fix vocab iteration
* regex space fix
* add kimi-k2 to pre_computed_hashes
* Updated with kimi-k2 get_vocab_base_pre hash
* fix whitespaces
* fix flake errors
* remove more unicode.cpp whitespaces
* change set_vocab() flow
* add moonshotai-Kimi-K2.jinja to /models/templates/
* update moonshotai-Kimi-K2.jinja
* add kimi-k2 chat template
* add kimi-k2
* update NotImplementedError
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com >
* except Exception
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com >
* LLM_CHAT_TEMPLATE_KIMI_K2 if(add_ass){}
---------
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com >
2025-07-15 21:54:22 +02:00
ba1ceb3456
vulkan: fix noncontig check for mat_mul_id splitting ( #14683 )
...
* vulkan: fix noncontig check for mat_mul_id splitting
Remove supports_op check for > 4096 (splitting fixes this)
* vulkan: fix batched matmul dequant for Q*_K
2025-07-15 21:51:09 +02:00
10a0351a97
vulkan: add RTE variants for glu/add/sub/mul/div ( #14653 )
2025-07-15 21:32:11 +02:00
68e37a61a7
model : add PLaMo-2 support ( #14560 )
...
* Add PLaMo-2 model using hybrid memory module
* Fix z shape
* Add cmath to include from llama-vocab.h
* Explicitly dequantize normalization weights before RoPE apply
* Revert unnecessary cast because the problem can be solved by excluding attn_k, attn_q when quantizing
* Use ATTN_K/Q_NORM for k,q weights to prevent quantization
* Remove SSM_BCDT that is not used from anywhere
* Do not duplicate embedding weights for output.weight
* Fix tokenizer encoding problem for multibyte strings
* Apply suggestion from @CISC
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com >
* Update src/llama-model.cpp
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com >
* Use LLM_FFN_SWIGLU instead of splitting ffn_gate and ffn_up
* Remove unnecessary part for Grouped Query Attention
* Fix how to load special token id to gguf
* Remove unused tensor mapping
* Update src/llama-model.cpp
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com >
* Remove llama_vocab_plamo2 class and replace it with llm_tokenizer_plamo2_session to follow the other tokenizer implementations
* Update src/llama-vocab.cpp
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
* Update convert_hf_to_gguf.py
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com >
* Update src/llama-model.cpp
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com >
* Update src/llama-model.cpp
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com >
* Update convert_hf_to_gguf.py
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com >
* Update convert_hf_to_gguf.py
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com >
* Fix plamo2 tokenizer session to prevent multiple calls of build()
---------
Co-authored-by: Francis Couture-Harpin <git@compilade.net >
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com >
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com >
2025-07-15 18:11:42 +02:00
ce7aa0d5c0
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# ggml/src/ggml-sycl/ggml-sycl.cpp
# requirements/requirements-all.txt
2025-07-15 23:59:53 +08:00
d3d5e36af6
backwards compat for older flags in config load
2025-07-15 22:05:57 +08:00
51cac6f30c
add a title to load config
2025-07-15 18:22:44 +08:00
8396add5be
removed hunyuan autoguess template, fixed multi file loading up to 999 parts
2025-07-15 17:49:49 +08:00
cbc68be51d
cuda: fix build warnings in set-rows.cu (unused variable) ( #14687 )
...
Python check requirements.txt / check-requirements (push) Failing after 15s
Python Type-Check / pyright type-check (push) Successful in 1m15s
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com >
2025-07-15 15:28:53 +08:00
f3f6168f85
added new autoguess templates
2025-07-15 14:51:20 +08:00
bdca38376f
sycl: Hotfix for non dnnl codepath ( #14677 )
2025-07-14 18:12:42 +01:00
4db8ba6228
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# ggml/src/ggml-sycl/gemm.hpp
# ggml/src/ggml-sycl/ggml-sycl.cpp
# ggml/src/ggml-sycl/set_rows.cpp
2025-07-14 23:16:44 +08:00
b7f8d0fe2b
handle inconsistent final message content being sent with finish_reason
2025-07-14 22:17:18 +08:00
55c509daf5
ggml : refactor llamafile_sgemm PPC code ( #14673 )
...
Remove un-necessary templates from class definition and packing functions
Reduce deeply nested conditionals, if-else switching in mnapck function
Replace repetitive code with inline functions in Packing functions
2 ~ 7% improvement in Q8 Model
15 ~ 50% improvement in Q4 Model
Signed-off-by: Shalini Salomi Bodapati <Shalini.Salomi.Bodapati@ibm.com >
2025-07-14 16:16:42 +03:00
9c9e4fc635
llama-context: add ability to get logits ( #14672 )
2025-07-14 21:01:41 +08:00
494c5899cb
scripts: benchmark for HTTP server throughput ( #14668 )
...
* scripts: benchmark for HTTP server throughput
* fix server connection reset
2025-07-14 13:14:30 +02:00
7e5582afdb
updated lite
2025-07-14 17:41:36 +08:00
0e8f96414a
add in backwards compatibility for older clients with incorrect json_schema passing
2025-07-14 17:41:08 +08:00
0f4c6ec0f1
SYCL: use 1D kernel for set_rows ( #14618 )
...
Python check requirements.txt / check-requirements (push) Failing after 13s
Python Type-Check / pyright type-check (push) Successful in 56s
* SYCL: Use 1D kernel for set_rows
* Remove dangling comment
* Refactor and use ceil_div
2025-07-14 10:37:55 +01:00
65a3ebb0aa
sycl: Batched mulmat rework for oneDNN dispatch ( #14617 )
2025-07-14 10:37:35 +01:00
0d9226763c
llama : add jinja template for rwkv-world ( #14665 )
...
* llama : add jinja template for rwkv-world
Signed-off-by: Molly Sophia <mollysophia379@gmail.com >
* Update convert_hf_to_gguf.py
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com >
---------
Signed-off-by: Molly Sophia <mollysophia379@gmail.com >
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com >
2025-07-14 07:43:43 +08:00
982e347255
quantize : fix minor logic flaw in --tensor-type ( #14572 )
2025-07-13 18:02:17 +02:00
aa3623dcce
remove unwanted workflow
2025-07-13 23:43:56 +08:00
bc2877d2fe
test without g3n fix
2025-07-13 23:42:59 +08:00
8cebec5128
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# CMakePresets.json
# README.md
# common/CMakeLists.txt
# ggml/src/ggml-cann/ggml-cann.cpp
# ggml/src/ggml-opencl/CMakeLists.txt
# ggml/src/ggml-opencl/ggml-opencl.cpp
# ggml/src/ggml-sycl/ggml-sycl.cpp
# scripts/sync-ggml.last
# tests/test-backend-ops.cpp
# tools/run/CMakeLists.txt
2025-07-13 23:39:41 +08:00
66755c8fe9
switch to miniaudio, support mp3 for whisper
2025-07-13 23:24:07 +08:00
923e3ea2e3
cuda : add set rows for bf16 ( #14664 )
Python check requirements.txt / check-requirements (push) Failing after 1m26s
Python Type-Check / pyright type-check (push) Successful in 4m13s
Update Operations Documentation / update-ops-docs (push) Successful in 14s
2025-07-13 15:01:24 +02:00
e7eb6d3200
increase default ctx size to 8k, rename usecublas to usecuda
2025-07-13 18:27:42 +08:00
811463a704
split audio and vision detection separately
2025-07-13 17:47:15 +08:00
e743cddb60
cuda : add ELU support ( #14657 )
2025-07-13 11:33:16 +02:00
05fec5bd29
ggml : add build-time message to remind about ggml_set_rows ( #14661 )
...
ggml-ci
2025-07-13 10:36:33 +03:00
dcf7f2ea3c
metal : Add missing unary ops Metal support ( #14660 )
2025-07-13 08:38:13 +03:00
84b396e051
cmake : Add CMake presets for Linux and GCC ( #14656 )
2025-07-13 08:12:36 +03:00
0938af7c83
fixed noscript image gen
2025-07-13 11:37:52 +08:00
6f4f1b7389
allowing resuming incomplete aria2 downloads
2025-07-13 11:14:39 +08:00
c31e60647d
tests : cover lfm2 cases in test_ssm_conv ( #14651 )
2025-07-12 19:10:14 +02:00
67eade1bf9
docs : add LFM2 to models section ( #14650 )
...
* readme : add LFM2 to models section
* fix copy paste...
2025-07-12 19:07:08 +02:00
8faf01016d
updated lite
2025-07-13 00:39:52 +08:00
7de5c7cab6
CUDA: add set rows for f32 and f16 ( #14551 )
...
* CUDA: add set rows for f32 and f16
* Review: change kernel params, use strides from host
* Use 1-d kernel
* Review: use int64_t for blockDim.x, rename nb->s for clarity
2025-07-12 16:31:38 +03:00
8eff95544e
sync : ggml
2025-07-12 16:13:27 +03:00
3120413ccd
vulkan : remove unused vars ( #0 )
...
ggml-ci
2025-07-12 14:25:44 +03:00
215535701d
sync : ggml
...
ggml-ci
2025-07-12 14:25:44 +03:00
74bb294591
vulkan : implement bilinear interpolation (ggml/1291)
...
ggml-ci
2025-07-12 14:25:44 +03:00
3e303b1107
vulkan : implement ggml_roll (ggml/1290)
...
ggml-ci
2025-07-12 14:25:44 +03:00
dca49de059
fixed qwen2 audio issues, works fine now (+3 squashed commit)
...
Squashed commit:
[b3053a1ba] updated lite
[5071630d6] fixed mtmd issues, audio works
[06efa5af4] fix mtmd compile
2025-07-12 18:54:41 +08:00
5a3b2e3921
fix for jamba models - they have recurrent layers like rwkv, so context shifting and forwarding wont work on them.
2025-07-12 18:54:40 +08:00
Concedo
Ed Addario
Gabriel Larson
Jeff Bolz
Shunta Saito
R0CKSTAR
Anton Mitkov
shalinib-ibm
Aman Gupta
Johannes Gäßler
Akarshan Biswas
Molly Sophia
Sigbjørn Skjæret
Yavor Ivanov
Georgi Gerganov
Tarek Dakhran
Acly