* Copy reduce result to other GPUs if necessary
* Avoid ggml_get_rows for TG
* For the output ops use the result of the split that ran on the main GPU
* More models
* A hopefully more efficient adaptive_p sampling
* Once at it, lets fix the formatting too
* More formatting
* Hopefully better
* This should be better
* Correctly accumulate adaptive_p sampling time
* AVX2
* A hopefully more efficient adaptive_p sampling
* Once at it, lets fix the formatting too
* More formatting
* Correctly accumulate sampling time for adaptive_p
* adaptive-p sampler: fix zeroed orig_probs bug and refactor
- Fix bug where original probabilities were captured as zero by calculating
them from logits in llama_prep_adaptive_p (new).
- Replace vector with unordered_map to track candidate probabilities,
filtering for relevance via logit delta (16.6f).
- Standardize API naming: llama_<action/verb>_<focus/name/topic>_<extra/info>
- Update function signatures to follow most other samplers.
* resolve merge bug
* adaptive-p: revert reordering function definitions
* WIP - not working
* WIP - not working
* WIP - GPT-OSS working
However, extremely stupid. The only way I could correctly repack the
up/gate experts is to copy up and gate into host buffers, repack
into another host buffer, copy back into the ffn_up_gate_exps tensor.
This is going to be very slow for giant 500 GB models.
My attempts to do this via a compute graph on the backend holding
the tensors was unsuccessful.
For GPT-OSS-20B I see ~6-7% better PP when using the original
ik_llama.cpp fused_up_gate CUDA implementation, and ~10% when
using the small batch size implementation.
Other models are not working yet on CUDA as I need to fix the
fused mul-unary implementation.
* WIP
* WIP - Qwen3-MoE (and hopefully all others) working
But when I say here and in the previous commit "working",
I mean PP is working. TG is still broken.
* WIP: TG seems to be working
* Minor
* Add command line option to merge experts up/gate
* Add merge up/gate command line parameter to llama-bench
* Turn off merge_up_gate_exps if split mode graph
It is not yet implemented
* When no bias, allow merging up/gate with tensor overrides
* Arghh, we need to increase the context size again
* Cleanup
* Mimo-2 support
* Fix bug for head sizes not being the same
It still does not solve the Mimo-2 quantized cache issue.
* Fix quantized cache
* Minor
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* WIP: absorb adding input into std_attn and std_ffn
* WIP: NCCL infra
* WIP: add reduce and fake_cpy ops
* WIP
* WIP: graph appears to work, layer is broken
* WIP: Qwen3-MoE works with graph, layer still broken
* WIP: GLM-4.5 graph works
* WIP: fix sm layer (dense)
* WIP: fix sm layer (MoE)
* WIP: fast PP with bespoke 4-GPU NCCL
I guess, I'm not using NCCL the right way as PP is very
low with a single communicator group for 3 or more GPUs.
But if I create 4 communicator groups for pairs of GPUs
(0,1, 2,3, 0,2, 1,3) and use that, PP is fast: I'm hitting
1500 t/s for L3-70B on the 4x3090 system, which is
~20% better than the previous sm graph without NCCL.
But that cannot be the solution (I cannot be creating pairwise
communicators and associated logic for every possible number of GPUs).
* WIP: Cohere2
* Explicitely set device
* Bespoke 3-GPU case
* WIP
* Do not repeat get_rows multiple times
* Fix 3 GPUs
* OK, let's leave it in
* Simple async
* This sync seems enough
* Only do async for 4 or more backends
With 2 GPUs (so, 3 backends) not using async is slightly faster
* Scheduler changes
* Use OpenMP if available
Surprisingly (at least to me), this is quite a bit faster than
std::thread and std::barrier. GLM-4.5-AIR with 4 GPUs is now
at 105 t/s at zero context!
* Do not use OpenMP if there are tensor overrides
* Set omp max active levels
* Be more careful with having set the device before using a stream
* Command line option to turn on async. Set to false by defualt for now
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Use -smgs or --split-mode-graph-scheduling in CLI to bypass the disabling of split mode graph scheduling when tensor overrides is used.
Co-authored-by: Kawrakow <iwankawrakow@gmail.com>
* This should do the trick for PP
* Command line option to set max. extra VRAM that the scheduler can use
* Fix bug and cleanup
* Looks like with this change it is working with tensor overrides
* Nah, it is not working
* OK, this seems to be working
* Disable split scheduling with tensor overrides
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* This works and TG is descent, but PP is low
* Better
* Apply f_logit_scale before mul mat with output tensor
* This is better for PP: 600 t/s -> 700 t/s
* To not lose this again
* WIP
* Equal split
* WIP
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Rearrange graph nodes
So that we can do graph portions that are the same on 2 or more
GPUs at the same time.
* Separate graph compute implementation for split mode graph
* This is better
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Required adding the "temperature scaling" to the standard attention
implementation.
But in this way split mode "graph" is automatically supported.
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Remove most of split mode row
* WIP
* WIP: also allocate the KV cache using tensor split
* WIP: it runs with wrong result
But it also looks like the backend scheduler is not going to help:
* It copies mask and input positions to GPU 0
* => RoPE ops must run on GPU 0
* => To proceed attn evaluation, GPU 1 must wait for GPU 0 to finish its
entire attn calculation
* Same with FFN. The rms_norm gets scheduled on GPU 0. Hence, GPU 1 must
wait for GPU 0 to finish its entore FFN calculation before it can
start (as it needs to copy the result of rms_norm from GPU 0)
* => Seems useless without writing a bespoke TP scheduling
* WIP
* This works, but it is slow
* This is slightly better
the graph is still not being computed in parallel.
Why? Because the scheduler creates graph splits where the
result of the computation on one GPU becomes an input for the
other split. Hence, to trigger the computation on the second GPU
one needs to wait for the computation on the first GPU to finish,
even thiough the two can be done in parallel up to the sunchronization
point. So, all that is left to do is to trick the scheduler to create
to splits that can be done in parallel, and then have a graph split
where the results get combined.
* Playing games with the scheduler
This change tricks it into doing the right thing^TM.
Still quite a bit slower than split mode layer for the 8B LlaMA model.
But for the 70B LlaMA it now beats split mode layer for TG:
28 t/s vs 24.4 t/s. PP is 627 t/s vs 744 t/s.
In comparison, split mode "row" in mainline gets
484 t/s PP and 19.3 t/s TG.
* Fix attn split
Granularity for Wq, Wo is not just head size, but
head size * gqa_ratio.
Else the Wk, Wv tensors end up not being a multiple of the
head size when we divide the split determined by Wo with
the gqa_ratio.
* Show memory used per device
* Make it work with partial offload
but no tensor overrides yet, just ngl < num_layers.
* Allow for f16 source in fused_rms_norm
* This results in faster PP.
Now PP is faster than split mode layer for L3-70B.
* Rename split mode "row" to split mode "graph"
* Leave FFN partial results as f16
* WIP GLM4.5 - runs with wrong results
* WIP GLM4.5 - this works
PP is already better than split mode layer, but TG for zero context
is kind of low - 60 vs 92 t/s. TG becomes better than split mode layer
at around 20k tokens. PP at 26k tokens is 1.55X of sm layer.
* Work around compiler bug
It issues a warning that there is an extra semicolon outside of a function,
but there isn't. If I remove the anonymous namespace and turn the
functions inside into static, the warning disapears, so clearly
a compiler bug.
* Make graph reuse work with split mode graph
* Remove more split mode row remnants
* WIP tensor overrides
Runs with wrong results, don't see where the issue could be.
* This works but is slow
Still does not work for row-interleaved quants
* Slightly better
* Slightly better
* Row-interleaved quants work
* Better
* Minor
* Guarad against using split mode "graph" for unsupported models
* Guards against using merge_qkv with split mode "graph"
* WIP split mode attn
Works for LlaMA models, but not for GLM-4.5.
Doesn't seem to improve performance, so I guess no point in trying to
fix it.
* Split mode graph for qwen3moe
* Try to better distribute the splits
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* RPC support multiple devices
* rpc : update documentation (#16441)
Update the README file to match the newly added functionality of
exposing multiple devices from a single server.
Co-authored-by: Diego Devesa <slarengh@gmail.com>
# Conflicts:
# examples/rpc/README.md
* Remove memory settings
* rpc : cache and reuse compute graphs (#15405)
Store the last computed graph and reuse it when possible.
Also do not return response from GRAPH_COMPUTE and assume it always
completes successfully. If this this is not the case, the server closes
the connection. This saves us a network round trip to the server.
* Add -cpu to include cpu backend
---------
Co-authored-by: firecoperana <firecoperana>
Co-authored-by: Radoslav Gerganov <rgerganov@gmail.com>
* model : Granite docling + Idefics3 preprocessing (SmolVLM) (#16206)
* feat: Add granite-docling conversion using trillion pretokenizer
Branch: gabe-l-hart/GraniteDocling
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Add granite-docling vocab pre enum
Branch: gabe-l-hart/GraniteDocling
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Use granite-docling pre
Branch: gabe-l-hart/GraniteDocling
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Add clip_is_idefics3
Branch: gabe-l-hart/GraniteDocling
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Allow multi-token boundary sequences for image templating
Branch: gabe-l-hart/GraniteDocling
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Add tiling support for idefices3 in clip.cpp
This should likely be moved into llava_uhd::get_slice_instructions, but for
now this avoids disrupting the logic there.
Branch: gabe-l-hart/GraniteDocling
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Partial support for full templating for idefics3 in mtmd
There are still errors encoding some of the image chunks, but the token
sequence now matches transformers _almost_ perfectly, except for the double
newline before the global image which shows up as two consecutive newline
tokens instead of a single double-newline token. I think this is happening
because the blocks are tokenized separately then concatenated.
Branch: gabe-l-hart/GraniteDocling
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Fully working image preprocessing for idefics3 w/ resize and slicing
Branch: gabe-l-hart/GraniteDocling
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* feat: Parse the preprocessor config's longest side and add it to the mmproj hparams
Branch: GraniteDocling
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Use the longest side instead of size * scale_factor
For Granite Docling, these come out to the same value, but that was just a
conicidence.
Branch: GraniteDocling
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* fix: Allow batch encoding and remove clip_is_idefics3
Branch: GraniteDocling
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* refactor: Remove unnecessary conditionals for empty token vectors
Branch: GraniteDocling
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* refactor: Use image_manipulation util
Branch: GraniteDocling
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
* add test model
---------
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
# Conflicts:
# convert_hf_to_gguf.py
# convert_hf_to_gguf_update.py
# gguf-py/gguf/constants.py
# gguf-py/gguf/gguf_writer.py
# src/llama-vocab.cpp
# src/llama-vocab.h
* mtmd : support home-cooked Mistral Small Omni (#14928)
* model : add LightOnOCR-1B model (#16764)
* model : add LightOnOCR-1B model
* add test
# Conflicts:
# convert_hf_to_gguf.py
# gguf-py/gguf/constants.py
* mtmd : fix idefics3 preprocessing (#16806)
* mtmd : fix idefics3 preprocessing
* disable granite test
* fix test for granite
* model: Add support for CogVLM model (#15002)
* Added GGUF mappings for CogVLM model
* Add tensor mapping for CogVLM visual encoder
* Add CogVLM to conversion script, no vision part yet
* Added CogVLM vision model to conversion script
* Add graph for CogVLM CLIP model
* Add graph for CogVLM
* Fixes for CogVLM. Now compiles.
* Model now runs
* Fixes for cogvlm graph
* Account for graph context change after rebase
* Changes for whitespace
* Changes in convert script according to comments
* Switch CogVLM LLM graph to merged QKV tensor
* Use rope_type variable instead of direct definition
* Change CogVLM CLIP encoder to use SWIGLU
* Switch CogVLM CLIP to use merged QKV
* Apply rebase edits and remove ggml_cont call that is now unnecessary
* clean up
---------
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
# Conflicts:
# convert_hf_to_gguf.py
# examples/mtmd/clip.cpp
# gguf-py/gguf/constants.py
# gguf-py/gguf/tensor_mapping.py
# src/llama-arch.cpp
# src/llama-arch.h
# src/llama-model.cpp
# src/llama-model.h
* mtmd: refactor preprocessing + support max/min pixels (#16878)
* mtmd: refactor preprocessing + support max/min pixels
* fix mlp type
* implement mix/max pixels
* improve hparams
* better image preproc for qwen
* fix
* fix out of bound composite
* fix (2)
* fix token calculation
* get_merge_kernel_size()
* fix llama4 and lfm2
* gonna fix them all
* use simple resize for qwen
* qwen: increase min tokens
* no resize if dst size == src size
* restore to initial min/max tokens value for qwen
# Conflicts:
# examples/mtmd/clip.cpp
* clip : use FA (#16837)
* clip : use FA
* cont : add warning about unsupported ops
* implement "auto" mode for clip flash attn
* clip : print more detailed op support info during warmup
* cont : remove obsolete comment [no ci]
* improve debugging message
* trailing space
* metal : remove stray return
---------
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
* model: add Janus Pro for image understanding (#16906)
* Add support for Janus Pro
* Update gguf-py/gguf/tensor_mapping.py
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* Update gguf-py/gguf/tensor_mapping.py
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* Address reviewer suggestions
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* Add JANUS_PRO constant
* Update clip model handling
Co-authored-by: Xuan-Son Nguyen <son@huggingface.co>
* Update tools/mtmd/clip.cpp
Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>
* Refactor JANUS_PRO handling in clip.cpp
Co-authored-by: Xuan-Son Nguyen <son@huggingface.co>
* Update tools/mtmd/clip.cpp
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* em whitespace
---------
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
Co-authored-by: Xuan-Son Nguyen <son@huggingface.co>
Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>
# Conflicts:
# convert_hf_to_gguf.py
# gguf-py/gguf/constants.py
# gguf-py/gguf/tensor_mapping.py
* mtmd: pad mask for qwen2.5vl (#16954)
* mtmd: pad mask for qwen2.5vl
* improve
* mtmd: add --image-min/max-tokens (#16921)
* mtmd: improve struct initialization (#16981)
* mtmd: allow QwenVL to process larger image by default (#17020)
* Disable flash attention
* mtmd : fix embedding size for image input (#17123)
* mtmd: fix patch_size initialized to random value in audio models (#17128)
* mtmd: fix patch_size initialized to random value in audio models
* add default hparams
* add llama_model_n_embd_inp
* Fix load qwen3 vl
Change batch size
* Add description
* Fix cli build error
---------
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
Co-authored-by: Tianyue-Zhao <zhaotianyue@outlook.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Zhiyong Wang <85110830+ravenouse@users.noreply.github.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>
Co-authored-by: firecoperana <firecoperana>
* Add mainline compatible FA command line option
* Graph reuse: add command line argument to turn it on
* WIP
* This seems to work
* This is perhaps cleaner
* Change the command line option to -gr
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
so more recent users that haven't followed the history of FlashMLA
evolution and hence don't know about the MLA options get the best setting
without having to add -mla 3 on the command line.
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Introducing rope cache
When computing RoPE, the rotation angles in each layer
are exactly the same, and only depend on the token positions
(and other constant, model dependent parameters).
So, I wonder, why don't we compute the angles just once
and then reuse for the Q and K RoPE in each layer?
This commit does it as a POC on the CPU, and uses it in
the Qwen3-MoE compute graph.
* cuda: neox works
* WIP
* rope_cache: norm works
* Fused rope+rope
* Fused rope+rope (norm)
* Fused rms+rms+rope+rope (neox) - not working
* WIP
* Also qwen3
* Add command line arg to disable rope cache
* Disable RoPE cache if rope type is not neox or norm
* Add missing break after merge with main
* Fused fused_rms+fused_rms+rope+rope (with -mqkv)
* Fused fused_rms+fused_rms+rope+rope (without -mqkv)
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* POC: merge Q, K, V into a single, contiguous tensor
Done just for Qwen3-MoE, where I see a 4% uplift in TG.
PP performance gain is sub-percent, if any.
Still, it seems it makes sense to do it in general given
the TG performance gain.
* WIP
* merge_qkv: it works for gpt-oss
...but we see a smaller TG gain (~1.5%)
* WIP
* Don't ignore the return value of create_tensors()
else, when q, k, v get merged and we are running on the CPU,
we get a crash because the backend is trying to use mmap,
but that no longer works.
* merge_qkv: bias can be required, optional, or mandatory
* merge_qkv: glm4.5moe
* merge_qkv: add command loine argument to enable
* merge_qkv: fix tensor dimensions
* merge_qkv: llama-4
* merge_qkv: qwen3 (dense)
* merge_qkv: simplify build_qwen3moe
* cohere2 - simplify graph building
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Change fmoe to be on by default
* Change default fmoe also in llama-bench
* Change flash attention to be on by default
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Adding fused mul+multi_add + CPU implementation
* fused mul+multi_add: CUDA
* fused mul+multi_add: command line argument to disable it
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Do not allocate KV cache for unused layers
* Do not apply experts weight scale if it is 1
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Better argsort (CPU)
* Attemt at grouped topk
* This seems to do the trick for grouped experts routing
* Cleanup
* Trying to merge, something is not right
* Working merged grouped top_k (CPU)
* Add command line option to enable grouped expert routing
* Add grouped expert routing option to llama-bench
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Parallelize mask
We see non-negligible PP gains for long contexts.
More importantly, the strange drop in performance
observed for GPT-OSS for context >= 32k tokens is gone.
* Whith FA on, create mask as f16 directly
* WIP
* Reduce KQ mask padding to 16
Why was it 64 in the first place?
I don't observe any issues, while TG performance
for long contexts improves by 2-4%.
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* llama_model and llama_hparams
* llama_build_context
Surprisingly small reduction in llama.cpp compile time given
the reduction in LOCs (22k -> 14k)
* LLM_TN
llama.cpp compilation: 50 s -> 33 s
* llama_quantize
* arch names
* All graph building is now in llm-build-context.cpp
* hparams loading
llama.cpp is now just 9300 LOC, but still takes 32 seconds to compile.
* We are now at 6 seconds to build the src folder
* load -> create
We are not actually loading the tensors, but just creating them.
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Add mtmd: the beginning
* Add mtmd: mtmd.cpp compiles
* Add mtmd: clip initialization compiles
* Add mtmd: clip.cpp compiles
* Add mtmd: builds successfully
* Add CPU implementation for GGML_OP_GLU
* Add CUDA implementation for GGML_OP_GLU
* Add CPU implementation for GGML_OP_CONV_2D and GGML_OP_CONV_2D_DW
* Add CUDA implementation for GGML_OP_CONV_2D and GGML_OP_CONV_2D_DW
* Add mtmd: refresh CPU rope
* Add mtmd: refresh CUDA rope
* Add mtmd: add Qwen2-VL
* Add mtmd: Qwen2.5-VL text seems to work with this change
* Add mtmd: fix swiglu
* Add mtmd: use LOG_TEE so generated tokens show up in terminal
* Add mtmd: do not attempt to load a GPU backend if none are available
* GLU, not GPU
* Fix typo
* Fix new/free mismatch
* LOG stuff
* Add mtmd: this fixes gibberish on second image
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Quick attempt to fuse the Q, K, V GEMMs
Doesn't do much on the CPU
* Doesn't do much on the GPU either
* Use llm_build_mul_mat_qkv
* This is not needed
* Revert timing on committed by mistake
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Offload only activated experts
* This seems to do the trick for -fmoe
* Do not recalculate activated expers for fused up/gate
* Log out of bounds access details
* Add a command line argument
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Bounds for flash attention
* Add n_swa to FA parameters
* Fix it
* This seems very slightly better
* Using vec kernel when we have SWA
* Need also this
* f32 vec kernel
* This is slightly better
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Fused up+gate+unary for regular (not MoE) FFN - CPU
* WIP CUDA
* Seems to be working on CUDA
For a dense model we get 2-3% speedup for PP and ~0.6% for TG.
* Add command line option
This time the option is ON by default, and one needs to turn it
off via -no-fug or --no-fused-up-gate
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Skip the row id computation for the ffn_down op
Sadly, almost negligible performance gain.
* Also this doesn't do much
* Also this barely moves the needle
* This is slightly better
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Check for NaNs while loading the model.
* Also tell which experts have NaNs.
* Add command line option to validate quants
* Add checks for more quantization types
* Add checks for more quantizagtion types
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* This does the trick for PP
* Compute mask bounds when creating the mask
* Set mask bounds for all supported SWA models
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* gmp-oss: common
* gpt-oss: attnetion sinks, swiglu_oai
* gpt-oss: WIP llama
Model loads and runs (CPU only), but PPL is much to high
(~1500 for 1st batch vs ~200 in mainline).
Is it because of SWA, because of vocab, or did I introduce a bug somewhere?
* gpt-oss: CPU seems to be working
It was the SWA thta was missing in the previous commit.
There are issues with EOG tokens, so this still needs to be added.
* CUDA: ADD_ID
Just a copy from mainline
* gpt-oss: Seems to be working on CUDA
* gpt-oss: add sinks to the attn-vec kernels
* CUDA: add head size of 64 to new mma
Haven't turned it on yet, but observe slightly better PP and slightly
worse TG performance with that.
* gpt-oss: add ability to use -fmoe (only CUDA for now)
* Move row sums to the write place
* Add sinks to iqk flash attention
* gpt_oss: Implement -fmoe on the CPU
* Simdify swiglu_oai
Turning it off for now as performance becomes more variable,
so perhaps I'm running into thermal trottling imore often
because of making the CPU work too hard.
* llama: factor out model loader
* Builds successfully
* It runs, but mmap does not work
* Fix llama_mmap so mmap works
* Minor
* Fix CUDA after latest changes
* Attempt to use CUDA graphs with MoE models - not working
* CUDA graphs WIP - still not working
* CUDA graphs - seems to be working
Likely not all MLA variants are working.
I no longer remember why I added the q8_0 cpy that
transposes the tensor, but if really needed, this is now
missing. Also missing is q6_0.
* Make q8_0 cache work for DeepSeek models with CUDA graphs
* cuda: cpy for q6_0
* Fix llama_mmap on non-Linux platforms
* Adding forgotten file
* Iterating on Windows build failures
* cuda: re-add q8_0 -> q8_0 transpose
so mla = 2 can be used with CUDA graphs and q8_0 cache.
* Disable graphs without -fmoe
* Minor
* Turn graphs on by default
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* mxfp4: basics
* mxfp4: Zen4 GEMM
* mxfp4: repacked GEMM (AVX2/Zen4)
* mxfp4: AVX2 GEMM
* mxfp4: NEON GEMM
* mxfp4: repacked GEMM (NEON)
* mxfp4: Metal
* Fix quantized K cache without FA (#680)
* Prevent assert with quantized K cache and no FA
* Fix MMQ when running with quantized K cache without FA
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Fix for Deepseek r1 parsing (#676)
* Implement function calling / tools for ik_llama.cpp for Kimi K2
* Implement basic tool choice
* Backport llama.cpp tool calls support
* Enhance function calls with improved chat parser and string utilities
- Add new chat.h/chat.cpp and chat-parser.h/chat-parser.cpp for better chat handling
- Improve function calls parsing with fallback to llama.cpp builder pattern
- Add string utility functions (starts_with, ends_with, find_partial_stop)
- Update README with function calls testing instructions
- Enhance Kimi K2 parser and function calls documentation
- Add comprehensive test suite for function calls
- Update CMakeLists.txt and Makefile for new components
* Enhance function calling with unified streaming and parser improvements
- Fix streaming content cleanup to prevent function syntax in output
- Unify content extraction patterns with llama.cpp approach
- Improve Kimi K2 parser robustness and partial content handling
- Add comprehensive test coverage for function call scenarios
- Optimize chat message parsing and diff computation
* Replace hardcoded values in kimi_k2_parser.hpp with named constants
- Add compile-time constants for all token format markers
- Add compile-time constants for XML format markers
- Add compile-time constants for simple format patterns
- Replace all hardcoded string literals with named constants
- Use compile-time length calculation to avoid manual counting
- Improve maintainability and reduce magic numbers throughout parser
* Fix duplicate common_chat_parse definition
- Remove duplicate implementation from chat-parser.cpp
- Keep single implementation in chat.cpp following llama.cpp patterns
- Resolves linker error: multiple definition of common_chat_parse
* Fix JSON assertion failure in function call parsing
- Add proper validation that 'function' field is an object before accessing nested keys
- Handle missing 'arguments' field gracefully with default "{}"
- Prevents crash when parsing malformed tool call JSON structures
* Add comprehensive Qwen3 XML tool calling support with unit tests
- Implement Qwen3 XML parser with <tool_call>{"name": "func", "arguments": {...}}</tool_call> format
- Add model detection and routing for Qwen3 vs Kimi-K2 formats
- Create 8 comprehensive unit tests covering parsing, streaming, error handling
- Fix token format cleaning bug in kimi_k2_parser.hpp processing order
- Remove progressive parsing code and related utilities
- Add tool injection support for Qwen3 format in server utils
* Add DeepSeek R1 function calling support with comprehensive unit tests
- Implement complete DeepSeek R1 tool call parsing in common_chat_parser.cpp
- Add DeepSeek R1 model detection and tool injection in deepseek_r1_tools.hpp
- Update function_calls.hpp with DeepSeek R1 integration and content extraction
- Update documentation to reflect support for Kimi-K2, Qwen3, and DeepSeek R1 models
- Add comprehensive unit tests for DeepSeek R1 reasoning, tool calls, and integration
- Port exact implementation patterns from original llama.cpp for compatibility
Key features:
- Native DeepSeek R1 format: <｜tool▁calls▁begin｜>function<｜tool▁sep｜>name```json{}```<｜tool▁call▁end｜><｜tool▁calls▁end｜>
- Reasoning content extraction from <think>...</think> tags
- Multiple tool calls support with separate call blocks
- Model detection for deepseek-r1, deepseek_r1 naming patterns
- Integration with incremental parsing and streaming support
* Add partial parsing support for JSON and regex
- json-partial.h/cpp: JSON partial parsing functionality
- regex-partial.h/cpp: Regex partial parsing functionality
* Add format_chat integration tests for Qwen3 tool injection
- Add test_qwen3_format_chat_integration() to validate tool injection pipeline
- Test tool injection conditions and system message enhancement
- Verify JSON formatting and anti-preamble instructions
- Add comprehensive test documentation
Tests confirm tool injection works correctly - conversational preamble
issue is not in ik_llama.cpp but likely in UI configuration.
* Fix Qwen3 tool call parsing - pass model name to parser
Server was not passing model name to parse_chat_message_incremental(),
causing Qwen3 to fall back to Kimi-K2 parser and return tool calls
as content instead of proper tool_calls array.
* Fix non-streaming path to use model-specific parsing
Non-streaming responses were hardcoded to use Kimi-K2 format,
causing Qwen3 XML tool calls to be returned as content instead
of proper tool_calls array. Now uses same model detection as
streaming path for consistency.
* Update Qwen3 function call handling in server and tests
- Enhanced server function call detection and response formatting
- Improved test coverage for Qwen3 tool call scenarios
- Refined XML parsing for better tool execution support
* Add DeepSeek-R1 function call parsing support
Implements comprehensive parsing for all 4 DeepSeek-R1 function call formats:
- Format 1: Standard function call syntax (already supported)
- Format 2: Alternative function call patterns (already supported)
- Format 3: Tools array format - function\n```json\n{"tools": [...]}
- Format 4: XML wrapped format - <tool_call>function</think>Name\n```json\n{...}```</tool_call>
Key changes:
- Added parse_deepseek_r1_tools_array() following original parse_prefixed_json_tool_call_array pattern
- Added parse_deepseek_r1_xml_wrapped() following Hermes-2-Pro XML wrapper patterns
- Integrated both parsers into exception handling chain for robust fallback
- Added comprehensive TDD test coverage for all formats
- Anonymized all confidential information while preserving functionality
Resolves tool_calls_count=0 issue where DeepSeek-R1 models generated valid tool calls
but server failed to parse them correctly.
* Update function_calls.md documentation for DeepSeek-R1 Format 4
- Added Format 4 (XML wrapped) documentation with examples
- Updated implementation notes with correct parser order (3→4→1→2)
- Marked all DeepSeek-R1 formats as working (July 2025 update)
- Updated test status for Format 3 and 4 as passing
- Added parse_deepseek_r1_xml_wrapped() function reference
- Corrected implementation file line numbers
* Fix merge conflict in test-function-calls.cpp
- Removed incomplete merge conflict marker from line 3027
- Ensured all tests compile and pass successfully
- All DeepSeek-R1 formats (1-4) working correctly
- All streaming and content cleaning tests passing
* Fix DeepSeek R1 parsing issue with responses wrapped in think tags
Restore missing consume_rest() call from working PR #648 implementation.
When responses don't contain tool calls, remaining content after reasoning
parsing must be preserved as displayable content.
Fixes issue where entire responses wrapped in <think> tags resulted in
empty content output.
* Implement proper reasoning handling following original llama.cpp patterns
- Add missing reasoning_format and reasoning_in_content fields to common_chat_syntax
- Update try_parse_reasoning to match original llama.cpp logic exactly
- Add TDD test case with reasoning_in_content=true for DeepSeek R1
- Following TDD: test should now pass with proper syntax configuration
Based on original llama.cpp implementation patterns.
* TDD SUCCESS: Fix DeepSeek R1 thinking tag termination issue
✅ Test passes with reasoning_in_content=true configuration
- Content properly preserved: '<think>content</think>' displays fully
- Reasoning field empty as expected
- Following TDD: test-first approach validates the fix
Next: Update server to automatically apply this configuration.
* Complete server integration fix for DeepSeek R1 thinking tag termination
- Server now automatically sets reasoning_in_content=true for DeepSeek R1 models
- Fixes issue where responses wrapped in <think> tags appear empty to users
* Add TDD test case for DeepSeek R1 thinking tag termination issue
- Test reproduces the exact failure scenario reported by user
- Validates that reasoning_in_content=true fixes the issue
- Demonstrates empty content problem and working solution
* Add remaining TDD test changes for DeepSeek R1 thinking tag fix
* Add debug output after upstream merge
* Remove temporary benchmark and debug files
- Remove tests/benchmark-progressive-parsing.cpp (development tool, not part of core functionality)
- Remove tests/reproduce_bug.sh (debugging script, not needed for PR)
* Port cpu moe options from mainline (#672)
* Port cpu moe options from mainline
* Use strdup and int32_t to follow coding guidelines
* maxfp4: CUDA dequantize
* mxfp4: CUDA GEMV
* mxfp4: CUDA MMQ
* mxfp4: minor CUDA tweaks
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Co-authored-by: Anton Sokolchenko <wsevendays@gmail.com>
Co-authored-by: Parsa <61601745+TheLegendOfKitty@users.noreply.github.com>
* iq1_kt: basics
* iq1_kt: CUDA dequantize
Testing with LlaMA-3.1-8B-Instruct, we get almost the same PPL
as iq2_xxs, so about 0.2 bpw fewer bits for the same quality.
* iq1_kt: CUDA MMQ
* iq1_kt: CUDA MMVQ
* iq1_kt: AVX2 GEMM/GEMV
* iq1_kt: convert/repack to q8_0_r8 (AVX2)
* iq1_kt: slightly faster GEMV
18.6 t/s -> 19.4 t/s
* iq1_kt: NEON GEMM/GEMV
Pathetic as usual
* iq1_kt: slightly faster NEON - still pathetic
* iq1_kt: tiny bit better GEMV on NEON
* iq1_kt: convert/repack to q8_0_r8 (NEON)
* iq1_kt: very slightly faster convert/repack to q8_0_r8 on NEON
* Adding frgotten file
* iq1_kt: add to constants.py
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* convert_hf_to_gguf for Kimi-K2-Instruct
Adapt mainline `PR14653` for tokenizer while maintaining proper MLA
tensors. Tested with this workflow using deepseek fp8_cast_bf16.py and
triton-cpu to upcast the fp8 safetensors to bf16 safetensors then used
this convert_hf_to_gguf.
* Add Kimi-K2 chat template
moonshotai/Kimi-K2-Instruct
https://github.com/ikawrakow/ik_llama.cpp/pull/609#issuecomment-3071259454
* kimi-k2 add ass to template to get response
* It compiles
* Seems to be working with coopmat
* Vulkan needs f32 precision for flash attention
* Vulkan: fix u_batch > 4096/n_active_experts
for coopmat1. Without this fix we get an assert.
We get the same assert in mainline too.
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
* Experiments for 2.6875 bpw quants
At least according to rmse, this is significantly better than
q2_K, while using only 1/16 more bits per weight.
* iq2_kl: basics
* iq2_kl: CUDA dequantize
* iq2_kl: small improvement in PPL
Also check the two neighbouring values for the block scale
and use the one that minimizes RMSE.
* iq2_kl: MMQ
Quite good: PP-512(L3-8B) = 8472 t/s.
* iq2_kl: MMVQ
We get PP-128(L3-8B) = 162 t/s.
Which means that this is not quite as good as it should be as
(almost) same bpq q2_K is at 170 t/s.
* iq2_kl: Zen4 GEMM/GEMV
Not particularly fast. I may need to think about rearranging the bits.
* iq2_kl: better Zen4
* iq2_kl: convert/repack to q8_k_r8 (AVX2)
* iq2_kl: AVX2 GEMM/GEMV
* iq2_kl: WIP NEON
The compiler started crashing!!!
* iq2_kl: NEON
Had to work around a compiler crash when using vzip2q_u8 using
vqtbl2q_u8.
* iq2_kl: convert/repack to q8_k_r8 (NEON)
* iq2_kl: Metal dequantize
* iq2_kl: Metal GEMV - pretty slow
* iq2_kl: Metal GEMV - slightly better (40 t/s -> 44.5 t/s)
* iq2_kl: Metal GEMV - slightly better (44.5 t/s -> 46.5 t/s)
* iq2_kl: Metal GEMV - slightly better (46.5 t/s -> 47.2 t/s)
* iq2_kl: slightly better Metal dequantize
PP-512 goes to 476 t/s up from 466 t/s.
* iq2_kl: slightly better Metal dequantize
PP-512 goes to 492 t/s up from 476 t/s.
* Add iq2_kl to constants.py
---------
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
To retain compatibility with : https://github.com/ikawrakow/ik_llama.cpp/pull/91
We need "else if" and not "if", otherwise the MOE and 70b condition takes precedence over the specified quant in the CLI.
* Add llama.cpp changes for dots1 support
* Add python changes for dots1 support
* Fix to make it convert
* Remove V reshaping, remove BOS by default for dots1 and fix warmup to handle models without BOS
* Minor fix
* Remove commented lines
Kawrakow
dungquixote42
firecoperana
firecoperana
Nexes the Elder
Thireus ☠
Downtown-Case
saood06
ubergarm
Aleksey Nikiforov
Fizz~