6d86944cb4
working through previous attemp, implimented more accurate conversion per previous attempt, added local sliding window attention that alternates every third layer
2025-09-03 14:32:39 -04:00
ca353d37b4
fixed pre tokenizer and still working through previous pr
2025-09-02 12:26:20 -04:00
c73eb685fd
added cls token per previous modern bert attempt, still working on checking out the rest
2025-08-29 12:15:31 -04:00
2a1c75047c
ubatch issues, the assert for checking equal seqs in llama-graph.cpp when building attention keeps failing, setting ubatch size to 1 when running llama-embedding with --ubatch-size 1 makes it work, but needs to be looked into more
2025-08-28 12:59:42 -04:00
853f344cfe
more cleanup
2025-08-28 12:47:10 -04:00
40249dd5ec
cleanup
2025-08-28 12:37:02 -04:00
9805635c12
cleanup
2025-08-28 12:36:26 -04:00
8f328431a1
cleanup
2025-08-28 12:33:52 -04:00
bffe3c9092
tensor debugging now works -> (llama-eval-callback), instead of simulated gate split with views, GEGLU is now used which does exactly this
2025-08-28 11:15:10 -04:00
18c0c23ed8
fixed tensor mappings and working on buildin graph
2025-08-27 15:32:20 -04:00
4ceb828112
correct tensor shape for qkv
2025-08-26 13:03:14 -04:00
cc3d7abab4
continuing
2025-08-26 12:38:38 -04:00
41b6864333
cleanup
2025-08-26 12:33:11 -04:00
cc40378d27
some cleanup
2025-08-25 16:31:08 -04:00
ac67fc6887
working on support, now working on building graph
2025-08-25 16:15:40 -04:00
6643c5a852
conversion now working, hf -> gguf
2025-08-21 12:42:32 -04:00
6151592ea7
constants and tensor mappings for modern bert support, model not supported yet but working on getting conversion to work for encoder only
2025-08-21 12:38:04 -04:00
79c1160b07
cuda: refactored ssm_scan and use CUB ( #13291 )
...
* cuda: refactored ssm_scan to use CUB
* fixed compilation error when when not using CUB
* assign L to constant and use size_t instead of int
* deduplicated functions
* change min blocks per mp to 1
* Use cub load and store warp transpose
* suppress clang warning
2025-08-09 20:29:43 +02:00
34c9d765bf
CUDA: add attention sinks for tile and wmma ( #15178 )
...
* CUDA: add attention sinks for tile and wmma
* Review: formatting changes + remove syncthreads from tile + remove warp_reduce_max from wmma
2025-08-09 20:00:24 +08:00
e54d41befc
gguf-py : add Numpy MXFP4 de/quantization support ( #15111 )
...
* gguf-py : add MXFP4 de/quantization support
* ggml-quants : handle zero amax for MXFP4
2025-08-08 17:48:26 -04:00
4850b52aed
server-bench: external OAI servers, sqlite ( #15179 )
...
* server-bench: external OAI servers, sqlite
* Update scripts/server-bench.py
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* Update scripts/server-bench.py
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* Update scripts/server-bench.py
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* raise_for_status
---------
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
2025-08-08 23:04:36 +02:00
cd6983d56d
ggml : fix field name when new ggml_backend ( #14944 )
2025-08-08 14:37:22 +02:00
6c7e9a5440
vendor: sync minja ( #15161 )
...
* vendor: sync minja
* Update minja.hpp
* Apply suggestions from code review
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
---------
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
2025-08-08 10:45:18 +01:00
1425f587a8
CUDA: attention sinks for mma FlashAttention ( #15157 )
2025-08-08 08:19:58 +02:00
aaa3d07ae7
opencl: support sink in `soft_max` (attn sinks) ( #15152 )
2025-08-07 21:47:03 -07:00
50aa938901
convert : support non-mxfp4 HF model ( #15153 )
...
* convert : support non-mxfp4 HF model
* rm redundant check
* disable debug check
2025-08-07 23:26:03 +02:00
c4f53563df
vulkan: support fattn sinks ( #15126 )
2025-08-07 22:44:20 +02:00
a0552c8bee
vulkan: Add env var to disable host visible vidmem ( #15109 )
2025-08-07 22:07:11 +02:00
99acbc9921
llama : Support intern-s1 ( #14875 )
...
* support internvl
* support interns1
* resolve comments
* put interns1 in tensor mapping
* resolve comment
* move tokenizer changes to sub class
2025-08-07 18:20:40 +02:00
7ad67ba9fe
HIP: add cmake option to enable compiler output of kernel resource usage metrics ( #15103 )
2025-08-07 16:44:14 +02:00
9a96389544
ggml: Skip backend library linking code when GGML_BACKEND_DL=ON ( #15094 )
...
Any available libraries are found and loaded dynamically at runtime.
2025-08-07 13:45:41 +02:00
1d72c84188
CUDA: GEMM for FP32/FP16/BF16 and ne11 <= 16 ( #15131 )
...
* CUDA: GEMM for FP32/FP16/BF16 and ne11 <= 16
2025-08-07 10:53:21 +02:00
20638e4f16
scripts: fix crash when --tool is not set ( #15133 )
2025-08-07 08:50:30 +02:00
36d3f00e14
requirements : fix PyTorch uint64 compatibility ( #15134 )
...
This commit addresses an issue with the convert_hf_to_gguf script
which is currently failing with:
```console
AttributeError: module 'torch' has no attribute 'uint64'
```
This occurred because safetensors expects torch.uint64 to be available
in the public API, but PyTorch 2.2.x only provides limited support for
unsigned types beyond uint8 it seems. The torch.uint64 dtype exists but
is not exposed in the standard torch namespace
(see pytorch/pytorch#58734 ).
PyTorch 2.4.0 properly exposes torch.uint64 in the public API, resolving
the compatibility issue with safetensors. This also required torchvision
to updated to =0.19.0 for compatibility.
Refs: https://huggingface.co/spaces/ggml-org/gguf-my-repo/discussions/186#68938de803e47d990aa087fb
Refs: https://github.com/pytorch/pytorch/issues/58734
2025-08-07 05:31:48 +02:00
5fd160bbd9
ggml: Add basic SET_ROWS support in WebGPU ( #15137 )
...
* Begin work on set_rows
* Work on set rows
* Add error buffers for reporting unsupported SET_ROWS indices
* Remove extra comments
2025-08-06 15:14:40 -07:00
756cfea826
fix profiling crash ( #15072 )
2025-08-06 14:17:51 -07:00
e725a1a982
opencl: add `swiglu_oai` and `add_id` ( #15121 )
...
* opencl: add `swiglu-oai`
* opencl: add `add_id`
* opencl: add missing `add_id.cl`
2025-08-06 12:12:17 -07:00
3db4da56a5
chat : support Granite model reasoning and tool call ( #14864 )
2025-08-06 20:27:30 +02:00
476aa3fd57
Fixed name `-override-tensors` to `-override-tensor` ( #15129 )
2025-08-06 17:28:48 +01:00
0d8831543c
ggml : fix fallback to CPU for ununsupported ops ( #15118 )
2025-08-06 14:37:35 +02:00
65c797c4fa
chat : fix yandex chat template ( #15116 )
2025-08-06 13:26:49 +02:00
25726898e8
chat : fix hunyuan auto-detection ( #15114 )
...
Signed-off-by: stevenkuang <stevenkuang@tencent.com>
2025-08-06 11:48:30 +02:00
2241453252
CANN: add support for ACL Graph ( #15065 )
...
* feat(cann): add optional support for ACL Graph execution
This commit adds support for executing ggml computational graphs using
Huawei's ACL graph mode via the USE_CANN_GRAPH flag. The support can be
enabled at compile time using the CMake option:
-DUSE_CANN_GRAPH=ON
By default, ACL graph execution is **disabled**, and the fallback path
uses node-by-node execution.
Key additions:
- CMake option to toggle graph mode
- Graph capture and execution logic using
- Tensor property matching to determine whether graph update is required
- Safe fallback and logging if the environment variable LLAMA_SET_ROWS
is unset or invalid
This prepares the backend for performance improvements in repetitive graph
execution scenarios on Ascend devices.
Signed-off-by: noemotiovon <757486878@qq.com>
* Fix review comments
Signed-off-by: noemotiovon <757486878@qq.com>
* remane USE_CANN_GRAPH to USE_ACL_GRAPH
Signed-off-by: noemotiovon <757486878@qq.com>
* fix typo
Signed-off-by: noemotiovon <757486878@qq.com>
---------
Signed-off-by: noemotiovon <757486878@qq.com>
2025-08-06 14:12:42 +08:00
9515c6131a
ggml: WebGPU disable SET_ROWS for now ( #15078 )
...
* Add paramater buffer pool, batching of submissions, refactor command building/submission
* Add header for linux builds
* Free staged parameter buffers at once
* Format with clang-format
* Fix thread-safe implementation
* Use device implicit synchronization
* Update workflow to use custom release
* Remove testing branch workflow
* Disable set_rows until it's implemented
* Fix potential issue around empty queue submission
* Try synchronous submission
* Try waiting on all futures explicitly
* Add debug
* Add more debug messages
* Work on getting ssh access for debugging
* Debug on failure
* Disable other tests
* Remove extra if
* Try more locking
* maybe passes?
* test
* Some cleanups
* Restore build file
* Remove extra testing branch ci
2025-08-05 16:26:38 -07:00
fd1234cb46
llama : add gpt-oss ( #15091 )
...
* oai moe
* compat with new checkpoint
* add attn sink impl
* add rope scaling yarn
* logits match with latest transformers code
* wip chat template
* rm trailing space
* use ggml_scale_bias
* rm redundant is_swa_all
* convert interleaved gate_up
* graph : fix activation function to match reference (#7 )
* vocab : handle o200k_harmony special tokens
* ggml : add attention sinks support (#1 )
* llama : add attn sinks
* ggml : add attn sinks
* cuda : add attn sinks
* vulkan : add support for sinks in softmax
remove unnecessary return
* ggml : add fused swiglu_oai op (#11 )
* ggml : add fused swiglu_oai op
* Update ggml/src/ggml-cpu/ops.cpp
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* update CUDA impl
* cont : metal impl
* add vulkan impl
* test-backend-ops : more test cases, clean up
* llama : remove unfused impl
* remove extra lines
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
---------
Co-authored-by: slaren <slarengh@gmail.com>
* repack mxfp4 upon conversion
* clean up a bit
* enable thinking
* add quick hack to render only some special tokens
* fix bf16 conversion
* remove vocab hack
* webui ok
* support chat parsing for gpt-oss
* fix webui
* direct mapping mxfp4, FINALLY
* force using mxfp4
* properly use lazy tensor
* ggml : add mxfp4
ggml : use e8m0 conversion instead of powf
Co-authored-by: Diego Devesa <slarengh@gmail.com>
change kvalues_mxfp4 table to match e2m1 (#6 )
metal : remove quantization for now (not used)
cuda : fix disabled CUDA graphs due to ffn moe bias
vulkan : add support for mxfp4
cont : add cm2 dequant
* ggml : add ggml_add_id (#13 )
* ggml : add ggml_add_id
* add cuda impl
* llama : add weight support check for add_id
* perf opt
* add vulkan impl
* rename cuda files
* add metal impl
* allow in-place ggml_add_id
* llama : keep biases on CPU with --cpu-moe
* llama : fix compile error
ggml-ci
* cuda : add fallback for __nv_cvt_e8m0_to_bf16raw
ggml-ci
* cleanup
ggml-ci
* sycl : fix supports_op for MXFP4
ggml-ci
* fix Unknown reasoning format
* ggml-cpu : fix AVX build
ggml-ci
* fix hip build
ggml-ci
* cuda : add mxfp4 dequantization support for cuBLAS
ggml-ci
* ggml-cpu : fix mxfp4 fallback definitions for some architectures
ggml-ci
* cuda : fix version required for __nv_cvt_e8m0_to_bf16raw
---------
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
Co-authored-by: slaren <slarengh@gmail.com>
2025-08-05 22:10:36 +03:00
f324a3b715
chat : only remove double bos/eos if added ( #15086 )
...
* only remove double bos/eos if added
* fix tests
2025-08-05 20:43:36 +02:00
be42642581
readme : update hot topics ( #15097 )
2025-08-05 20:19:33 +03:00
3306ceabf0
sycl: fix mul_mat selection ( #15092 )
2025-08-05 18:39:55 +02:00
c81de6e107
Fix `glm4moe` bug ( #15088 )
2025-08-05 13:56:44 +01:00
22f060c9c4
webui: fix markdown table ( #15081 )
...
* webui: fix markdown table
* webui: fix table display with themes
2025-08-05 13:56:44 +02:00
ryan-mangeno
David Zhao
Aman Gupta
compilade
Johannes Gäßler
AN Long
Olivier Chafik
lhez
Xuan-Son Nguyen
Jeff Bolz
RunningLeon
uvos
Christian Kastner
Daniel Bevenius
Reese Levine
rmatif
Sachin Desai
Juk Armstrong
Diego Devesa
Sigbjørn Skjæret
stevenkuang
Chenguang Li
Georgi Gerganov
Romain Biessy
Alex Wu