da7fd4aa57
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .devops/musa.Dockerfile
# .github/workflows/build.yml
# README.md
# ci/README.md
# docs/docker.md
# examples/lookahead/lookahead.cpp
# examples/lookup/lookup.cpp
# examples/parallel/parallel.cpp
# ggml/src/ggml-musa/CMakeLists.txt
# ggml/src/ggml-sycl/ggml-sycl.cpp
# tests/test-arg-parser.cpp
2025-05-21 23:12:22 +08:00
9f976e9c65
swa full used unless ctx shift and fast forward disabled
2025-05-21 22:47:45 +08:00
be0239693c
model : fix llama4 graph ( #13663 )
...
ggml-ci
2025-05-20 19:21:04 +03:00
e298d2fbd0
kv-cache : add SWA support ( #13194 )
...
* kv-cache : prepare for SWA
ggml-ci
* kv-cache : initial iSWA implementation
ggml-ci
* kv-cache : rework error recovery logic
ggml-ci
* models : fix Phi-3 SWA parameters
ggml-ci
* model : adjust Granite to rope factor changes
ggml-ci
* server : check if context can do shifts
ggml-ci
* iswa : for now, always enable shifts (experiment)
ggml-ci
* kv-cache : simplify SWA logic
ggml-ci
* kv-cache : apply defrag when we fail to find slots for the batch
ggml-ci
* llama : update docs about llama_decode
ggml-ci
* kv-cache : update warning logs when no space for the batch is available
ggml-ci
* llama : add llama_kv_self_seq_pos_min()
* kv-cache : keep track of partial SWA computes and print warnings
* server : disallow use cases involving partial SWA context
ggml-ci
* llama : add param to control SWA cache size
ggml-ci
* minor : clean-up
ggml-ci
2025-05-20 08:05:46 +03:00
e5d26a2356
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# common/CMakeLists.txt
# docs/backend/SYCL.md
# ggml/CMakeLists.txt
# ggml/src/ggml-sycl/CMakeLists.txt
# ggml/src/ggml-sycl/binbcast.cpp
# ggml/src/ggml-sycl/convert.cpp
# ggml/src/ggml-sycl/dequantize.hpp
# ggml/src/ggml-sycl/dmmv.cpp
# ggml/src/ggml-sycl/gemm.hpp
# ggml/src/ggml-sycl/ggml-sycl.cpp
# ggml/src/ggml-sycl/mmvq.cpp
# ggml/src/ggml-sycl/vecdotq.hpp
# ggml/src/ggml-vulkan/CMakeLists.txt
# ggml/src/ggml-vulkan/vulkan-shaders/CMakeLists.txt
# ggml/src/gguf.cpp
# scripts/compare-llama-bench.py
# tests/CMakeLists.txt
# tests/test-chat.cpp
# tools/llama-bench/llama-bench.cpp
# tools/server/README.md
2025-05-16 15:30:31 +08:00
12e6928ec2
i'm gonna regret this, aren't i?
2025-05-15 23:59:55 +08:00
5e7d95e22e
fix: Move build_inp_pos to the top of the graph section for build_granite ( #13538 )
...
This matches how others do it, but will still avoid the extra
initialization when rope is disabled.
Branch: GraniteFour
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com >
2025-05-14 15:53:59 +03:00
d590cd4c24
model : Granite MoE shared ( #13269 )
...
* feat: Add GGUF conversion for granitemoeshared
Branch: GraniteMoEShared
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com >
* feat: hparam and arch plumbing for granitemoeshared
Branch: GraniteMoEShared
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com >
* fix: Split MoE fused tensors for shared experts in conversion
Branch: GraniteMoEShared
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com >
* feat: First WIP cut at model arch in cpp
The hparam and architecture plumbing should be correct, but the
implementation of the shared experts seems to still be broken.
Branch: GraniteMoEShared
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com >
* fix: Cleaner (maybe more correct?) splitting for gate/up
Branch: GraniteMoEShared
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com >
* fix: Fix the input to the shared experts
I had misread that the shared experts take the inputs _before_ the standard
MoE layer and was feeding the output of the MoE to the shared experts.
Branch: GraniteMoEShared
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com >
* fix: Avoid architecture-specific checks for Granite MoE Shared
This is a cleaner way that will allow more flexibility in architecture
strings going forward.
Branch: GraniteMoEShared
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com >
* refactor: Split granite architectures out of llm_build_llama
This helps de-clutter the llama-family graph construction and allows
granite to diverge further (in preparation for Granite 4).
NOTE: I removed the granite scale factors from llm_build_deci because they
appear to only be there as copy-paste from llm_build_llama. The HF config
does not seem to set those values:
https://huggingface.co/Deci/DeciLM-7B/blob/main/config.json
Branch: GraniteMoEShared
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com >
* fix: Fix compiler warning about uninitialized inp_pos
This should not have been reachable, but it warns on some compliers
Branch: GraniteMoEShared
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com >
* fix: Consoladate GraniteMoEShared into GraniteMoE for conversion
Branch: GraniteMoEShared
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com >
* fix: Consolidate GraniteMoEShared into GraniteMoE on the c++ side
Branch: GraniteMoEShared
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com >
---------
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com >
2025-05-13 15:12:01 +02:00
21e31e255b
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/workflows/build.yml
# .github/workflows/docker.yml
# README.md
# build-xcframework.sh
# common/CMakeLists.txt
# examples/CMakeLists.txt
# ggml/src/ggml-cpu/CMakeLists.txt
# ggml/src/ggml-cuda/CMakeLists.txt
# ggml/src/ggml-metal/ggml-metal.m
# ggml/src/ggml-metal/ggml-metal.metal
# ggml/src/ggml-sycl/CMakeLists.txt
# ggml/src/ggml-sycl/backend.hpp
# ggml/src/ggml-sycl/common.hpp
# ggml/src/ggml-sycl/ggml-sycl.cpp
# ggml/src/ggml-sycl/mmvq.cpp
# ggml/src/ggml-sycl/vecdotq.hpp
# scripts/compare-llama-bench.py
# src/CMakeLists.txt
# src/llama-model.cpp
# src/llama.cpp
# tests/test-backend-ops.cpp
# tests/test-opt.cpp
# tools/llama-bench/README.md
# tools/llama-bench/llama-bench.cpp
# tools/mtmd/CMakeLists.txt
# tools/mtmd/README.md
# tools/mtmd/clip.cpp
# tools/rpc/rpc-server.cpp
# tools/server/CMakeLists.txt
# tools/server/README.md
2025-05-13 00:28:35 +08:00
10d2af0eaa
llama/ggml: add LLM training support ( #10544 )
...
* llama/ggml: add LLM training support
more compact progress bar
llama_save_model_to_file
llama_opt_param_filter
ggml_graph_dup force_grads
refactor ggml_opt, fix test-opt
* remove logits_all
* refactor CUDA implementation for ACC
* reset graph at beginning of opt period
2025-05-12 14:44:49 +02:00
6bb44391bd
Merge commit '5c86c9ed3ef1cc7307fdce05f0f0e2e45253cf90' into concedo_experimental
...
# Conflicts:
# tools/imatrix/imatrix.cpp
# tools/mtmd/README.md
# tools/run/README.md
# tools/run/run.cpp
2025-05-10 00:30:18 +08:00
27ebfcacba
llama : do not crash if there is no CPU backend ( #13395 )
...
* llama : do not crash if there is no CPU backend
* add checks to examples
2025-05-09 13:02:07 +02:00
3f96aeff39
llama : one-off chat template fix for Mistral-Small-2503 ( #13398 )
...
* llama : one-off chat template fix for Mistral-Small-2503
* update readme
* add mistral-v7-tekken
2025-05-09 11:17:51 +02:00
2439014a03
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/workflows/build.yml
# examples/embedding/embedding.cpp
# tools/imatrix/imatrix.cpp
# tools/perplexity/perplexity.cpp
2025-05-08 23:41:02 +08:00
b6220669f4
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/workflows/docker.yml
# Makefile
# examples/CMakeLists.txt
# ggml/CMakeLists.txt
# ggml/src/CMakeLists.txt
# ggml/src/ggml-sycl/common.hpp
# ggml/src/ggml-sycl/convert.cpp
# ggml/src/ggml-sycl/convert.hpp
# ggml/src/ggml-sycl/ggml-sycl.cpp
# scripts/sync-ggml.last
2025-05-08 23:07:33 +08:00
6562e5a4d6
context : allow cache-less context for embeddings ( #13108 )
...
* context : allow cache-less context for embeddings
ggml-ci
* context : enable reranking with encode()
ggml-ci
* context : encode() clears embd_seq
ggml-ci
* examples : use llama_encode() when appropriate
ggml-ci
* models : nomic bert moe does not require KV cache
* llama : update comments for llama_decode/llama_encode
ggml-ci
* context : update warning log [no ci]
2025-05-08 14:28:33 +03:00
f061021206
llama : print size and type of overridden tensors ( #13364 )
2025-05-08 13:15:15 +02:00
bc4e1128f7
llama : deci : support ffn-free with attention ( #13296 )
2025-05-07 12:49:27 +02:00
6c7fd67b64
llama : support tie embedding for chatglm models ( #13328 )
2025-05-07 09:23:11 +02:00
1377a93a73
Merge commit '5215b91e9377ce23e4ccc92ec3156bf5c7f892a3' into concedo_experimental
...
# Conflicts:
# .github/workflows/build.yml
# cmake/x64-windows-llvm.cmake
# ggml/src/ggml-rpc/ggml-rpc.cpp
# ggml/src/ggml-sycl/ggml-sycl.cpp
# tests/CMakeLists.txt
# tools/imatrix/imatrix.cpp
# tools/llava/clip.cpp
# tools/rpc/rpc-server.cpp
2025-05-06 23:15:04 +08:00
3bf785f3ef
llama : Llama-3_1-Nemotron-Ultra-253B-v1 support ( #12843 )
2025-05-03 17:39:51 +02:00
0951ad9f58
temp merge, not working
2025-05-03 11:42:01 +08:00
2f567611c0
llama-model : support Qwen2 embedding models and pooling_mode_lasttoken ( #13245 )
2025-05-02 11:42:30 -04:00
c642bc014c
kv-cache : separate recurrent vs non-recurrent impl ( #12799 )
...
* kv-cache : serparate recurrent vs non-recurrent impl (wip)
ggml-ci
* kv-cache : init -> contructor + add llama_memory_params
ggml-ci
* kv-cache : fix callback reference
ggml-ci
* context : llama_kv_cache -> llama_memory_i
ggml-ci
* context : move memory creation logic to model
ggml-ci
* llama : remove reference of memory during encode
ggml-ci
* kv-cache : hide padding details in the implementation
ggml-ci
* kv-cache : add ubatch_next()
ggml-ci
* context : simplify sbatch logic
ggml-ci
* kv-cache : hide defrag logic in the implementation
ggml-ci
* context : hide kv cache details in implementation
ggml-ci
* build : fix
ggml-ci
* cont : another fix
ggml-ci
* kv-cache : simplify interface (wip)
ggml-ci
* kv-cache : use separate KV cell structs for unified/recurrent
ggml-ci
* kv-cache : clean-up
ggml-ci
* model : better llama_model::create_model() signature
ggml-ci
* kv-cache : fix recurrent seq_rm()
ggml-ci
* kv-cache : replace `struct callbacks` with `llama_model &`
ggml-ci
* kv-cache : replace `struct graph_params` with `llama_context &`
ggml-ci
* kv-cache : fix offload check
ggml-ci
* context : avoid passing unique_ptr
ggml-ci
* kv-cache : avoid using the backends from the llama_context
ref #13113
ggml-ci
* kv-cache : more consistent debug logs [no ci]
* kv-cache : do not pass the full llama_context for kv graphs
ggml-ci
* kv-cache : remove comment
* kv-cache : ggml_rope_ext_inplace -> ggml_rope_ext
ggml-ci
* kv-cache : fix recurrent multi-user case
ggml-ci
* memory : remove comments [no ci]
2025-05-02 17:48:36 +03:00
17cbf9fd49
plamo fixed
2025-05-02 22:46:17 +08:00
cb06a3c363
llama : orion rope type is neox ( #13261 )
2025-05-02 12:44:24 +02:00
626083faf7
llama : plamo rope type is neox ( #13260 )
2025-05-02 12:40:56 +02:00
ca53d1bedc
Merge commit '13c9a3319b65469e883c49dd1c478abedc410157' into concedo_experimental
...
# Conflicts:
# ggml/src/ggml-cpu/CMakeLists.txt
# scripts/sync-ggml.last
# tests/test-backend-ops.cpp
2025-05-02 16:42:16 +08:00
a70183eb00
llama-model : fix the reported size class for nomic-embed-text-v2-moe ( #13223 )
2025-05-01 10:09:41 +03:00
8273739412
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .devops/cpu.Dockerfile
# .devops/cuda.Dockerfile
# .devops/intel.Dockerfile
# .devops/llama-cli-cann.Dockerfile
# .devops/musa.Dockerfile
# .devops/rocm.Dockerfile
# .devops/vulkan.Dockerfile
# examples/llama-bench/llama-bench.cpp
# examples/rpc/rpc-server.cpp
# scripts/compare-llama-bench.py
# tests/test-quantize-stats.cpp
2025-04-30 17:22:18 +08:00
cdf76586b2
CUDA: fix non-cont. inputs for batched mat mul ( #13155 )
2025-04-29 16:00:27 +02:00
b2ecfa0f55
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# README.md
# examples/llama-bench/README.md
# examples/llama-bench/llama-bench.cpp
# examples/llava/CMakeLists.txt
# ggml/src/ggml-rpc/ggml-rpc.cpp
# ggml/src/ggml-sycl/common.hpp
# ggml/src/ggml-sycl/element_wise.cpp
# ggml/src/ggml-sycl/element_wise.hpp
# ggml/src/ggml-sycl/ggml-sycl.cpp
# tests/test-chat-template.cpp
2025-04-29 21:05:16 +08:00
7d3af70b08
llama : llm_type order by size ( #13177 )
2025-04-29 13:25:53 +02:00
e98b3692be
llama : set qwen3 model type sizes ( #13175 )
2025-04-29 11:00:31 +02:00
5f5e39e1ba
model : Nomic Embed Text V2 with Mixture-of-Experts (MoE) architecture ( #12466 )
...
* Nomic Embed Text V2 with Mixture-of-Experts (MoE) architecture
- Adds MoE-based embedding model supporting multilingual embeddings.
- Selects architecture variant based on hyperparameter detection (MoE layers).
- Removes unnecessary subclass initialization checks for clarity.
https://www.nomic.ai/blog/posts/nomic-embed-text-v2
Co-authored-by: Jared Van Bortel <jared@nomic.ai >
* fix tokenizer
* don't rename this tensor
---------
Co-authored-by: Jared Van Bortel <jared@nomic.ai >
2025-04-28 22:52:15 +03:00
69699be48a
CUDA: fix q_nope_absorbed prec for DS 2 Lite f16 ( #13137 )
2025-04-28 09:29:26 +02:00
bce519cee7
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# ggml/src/ggml-cann/aclnn_ops.cpp
# ggml/src/ggml-cann/aclnn_ops.h
# ggml/src/ggml-cann/common.h
# ggml/src/ggml-cann/ggml-cann.cpp
# tests/test-backend-ops.cpp
2025-04-18 12:44:20 +08:00
2f74c354c0
graph : make FA compatible with MLA + add initial Metal kernels ( #12953 )
...
* graph : make mla compatible with FA
* metal : add exp FA kernels for DeepSeek models
ggml-ci
* llama : minor naming updates
ggml-ci
* ggml : disable FA for DS head sizes
* tests : add FA tests for MLA shapes
ggml-ci
2025-04-17 18:16:36 +03:00
06159939d9
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/workflows/build.yml
# Makefile
# docs/build.md
# examples/rpc/rpc-server.cpp
# examples/sycl/build.sh
# ggml/CMakeLists.txt
# ggml/src/ggml-cann/aclnn_ops.cpp
# ggml/src/ggml-cann/ggml-cann.cpp
# ggml/src/ggml-hip/CMakeLists.txt
# scripts/sync-ggml.last
2025-04-17 00:52:37 +08:00
daa422881a
llama : DeepSeek V2/V3 MLA implementation ( #12801 )
...
* Merged using squash to remove all noise commit messages
* Force flash attention off for `LLM_ARCH_DEEPSEEK2` - embedding too large
* Removed 3 conts (2x RoPE and 1x RMS-norm)
* Changed to use `<cmath>` instead of `<math.h>`
* Reverted removal of the 3 conts
* Used `reshape` in `llm_graph_context::build_attn_mha()`
* Use `k_pe = ggml_reshape`
* Removed the 3 conts again
* Removed the 3D views of `wk_b` and `wv_b`, and just save and 3D in GGUF
* Removed MQA optimisation from `build_attn_mha()` as no gains now
* Simplified `is_mla` branch in `llm_build_deepseek2()`
* Removed `build_attn_mla` and added `nullptr` to all `build_atnn` calls
* Fixed call to `build_attn` in `llm_build_t5_enc`
2025-04-15 09:49:57 +03:00
a0ae187563
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/workflows/docker.yml
# README.md
# build-xcframework.sh
# examples/llava/CMakeLists.txt
# examples/llava/clip.cpp
# examples/rpc/rpc-server.cpp
# examples/run/run.cpp
# ggml/src/ggml-cann/ggml-cann.cpp
# scripts/sync-ggml-am.sh
# scripts/sync-ggml.last
# tests/test-backend-ops.cpp
# tests/test-chat.cpp
2025-04-12 10:06:47 +08:00
ea9bd61e47
Merge commit '64eda5deb9859e87a020e56bab5d2f9ca956f1de' into concedo_experimental
...
# Conflicts:
# .devops/cuda.Dockerfile
# .devops/intel.Dockerfile
# .devops/llama-cli-cann.Dockerfile
# .devops/musa.Dockerfile
# .devops/rocm.Dockerfile
# .devops/vulkan.Dockerfile
# .github/workflows/build.yml
# .github/workflows/docker.yml
# README.md
# docs/backend/SYCL.md
# examples/llava/clip.cpp
# examples/server_embd.py
# ggml/src/ggml-cann/acl_tensor.cpp
# ggml/src/ggml-cann/aclnn_ops.cpp
# ggml/src/ggml-cann/aclnn_ops.h
# ggml/src/ggml-cann/ggml-cann.cpp
# src/CMakeLists.txt
# tests/test-chat-template.cpp
2025-04-12 08:31:22 +08:00
06bb53ad9b
llama-model : add Glm4Model implementation for GLM-4-0414 ( #12867 )
...
* GLM-4-0414
* use original one
* Using with tensor map
* fix bug
* change order
* change order
* format with flask8
2025-04-11 12:10:10 +02:00
8b91d5355a
llama : correct rms norm for llama 4 ( #12882 )
2025-04-11 08:49:50 +02:00
d3bd7193ba
llama : Support Qwen3 and Qwen3MoE ( #12828 )
...
* add qwen3 & qwen3moe support.
* fix
---------
Co-authored-by: bozheng-hit <dsoul0621@gmail.com >
2025-04-09 11:47:36 +02:00
ebf924c5d1
Merge branch 'upstream' into concedo_experimental
2025-04-08 21:46:30 +08:00
1466621e73
llama : Support llama 4 text-only ( #12791 )
...
* llama4 conversion
* initial support, no chat template
* clean up a bit
* fix tokenizer conversion
* correct hparams
* try this
* fix shexp
* ffn_inp_normed
* chat template
* clean up model conversion
* add_bos
* add scale_before_ffn
* fix order
* weight_before_ffn
* llm_graph_input_attn_temp
* add chunk attn mask
* build_inp_attn_scale()
* add comment about ggml_repeat
* clarify comments
* fix build
2025-04-07 23:06:44 +02:00
103d60ed2c
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# common/common.cpp
# examples/batched-bench/batched-bench.cpp
# examples/batched/batched.cpp
# examples/export-lora/export-lora.cpp
# examples/gritlm/gritlm.cpp
# examples/parallel/parallel.cpp
# examples/passkey/passkey.cpp
# examples/speculative-simple/speculative-simple.cpp
# examples/speculative/speculative.cpp
# ggml/src/ggml-cann/CMakeLists.txt
# ggml/src/ggml-cann/acl_tensor.cpp
# ggml/src/ggml-cann/acl_tensor.h
# ggml/src/ggml-cann/aclnn_ops.cpp
# ggml/src/ggml-cann/aclnn_ops.h
# ggml/src/ggml-vulkan/CMakeLists.txt
# tests/test-arg-parser.cpp
# tests/test-backend-ops.cpp
2025-04-03 18:57:49 +08:00
e0e912f49b
llama : add option to override model tensor buffers ( #11397 )
...
* llama : add option to override tensor buffers
* ggml : fix possible underflow in ggml_nbytes
2025-04-02 14:52:01 +02:00
9e182b3e78
Merge branch 'upstream' into concedo_experimental
...
# Conflicts:
# .github/workflows/build.yml
# README.md
# docs/backend/SYCL.md
# ggml/src/ggml-sycl/CMakeLists.txt
# ggml/src/ggml-vulkan/CMakeLists.txt
# ggml/src/ggml-vulkan/ggml-vulkan.cpp
# scripts/sync-ggml.last
# tests/test-chat-template.cpp
2025-04-01 20:16:07 +08:00
Concedo
Georgi Gerganov
Gabe Goodhart
Johannes Gäßler
Diego Devesa
Xuan-Son Nguyen
Sigbjørn Skjæret
piDack
ymcki
Jared Van Bortel
AT
Juk Armstrong
Yuxuan Zhang
Bo Zheng