d2b10302ce4e515202f5635185681819dcbc77ba
1627 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Georgi Gerganov
|
d2b10302ce | improve grader | ||
|
Georgi Gerganov
|
68dde884d6 | minor | ||
|
Georgi Gerganov
|
fd90796da2 | eval : support multiple dataset runs | ||
|
Georgi Gerganov
|
8156d549f6 | sim : fix answer matching | ||
|
Georgi Gerganov
|
9695e6feb4 | test : fix path | ||
|
Georgi Gerganov
|
fb1481d60d | eval : add prompts | ||
|
Georgi Gerganov
|
812ae13ec1 | eval : print progress | ||
|
Georgi Gerganov
|
e79e8d02d5 | examples: add task summary table to llama-eval-new.py | ||
|
Georgi Gerganov
|
a939f4c47e |
docs: update llama-eval-discussion.md with threading and model parameter updates
- Add threading support implementation details - Document ThreadPoolExecutor usage and thread safety - Add model parameter implementation details - Include testing results for both features |
||
|
Georgi Gerganov
|
62b04cef54 |
examples: add threading support and model parameter to llama-eval-new.py
- Add ThreadPoolExecutor for parallel request processing controlled by --threads - Add --model argument to specify model name in request data - Refactor process() to use thread-safe _process_single_case() method - Update progress tracking to work with concurrent execution |
||
|
Georgi Gerganov
|
37b26cafee | docs: update llama-eval-discussion.md with session work summary | ||
|
Georgi Gerganov
|
04f6872116 | examples: use cached dataset path in simulator to avoid HF Hub requests | ||
|
Georgi Gerganov
|
c2619c18bf | examples: use cached dataset path to avoid HF Hub requests | ||
|
Georgi Gerganov
|
87f8930968 | examples: remove HF_HUB_OFFLINE to allow dataset download | ||
|
Georgi Gerganov
|
9453f9de12 | examples: use HF_HUB_OFFLINE to avoid HF Hub warnings | ||
|
Georgi Gerganov
|
5a1be6ce37 |
examples: implement flexible grader system for answer validation
- Add Grader class supporting regex and CLI-based grading - Implement built-in regex patterns for AIME, GSM8K, MMLU, HellaSwag, ARC, WinoGrande - Add CLI grader interface: python script.py --answer <pred> --expected <gold> - Add HF telemetry disable to avoid warnings - Support exact match requirement for regex patterns - Add 30-second timeout for CLI grader - Handle both boxed and plain text formats for AIME answers |
||
|
Georgi Gerganov
|
a80814e97b | docs: remove README.md from llama-eval | ||
|
Georgi Gerganov
|
5cc2258e82 |
examples: add simplified llama-eval-new.py for AIME evaluation
- Create new simplified evaluation script focused only on AIME - Implement EvalState and Processor dataclasses for structured state management - Add real-time feedback showing correct/incorrect status per case - Abstract grading interface for external grader support - Use structured JSON output for eval state - Apply HuggingFace dataset caching to avoid repeated downloads - Remove Levenshtein matching - eval script only sends requests and validates answers |
||
|
Georgi Gerganov
|
c87af1d527 |
docs: update llama-eval-discussion.md with session work summary
Add summary of llama-server-simulator implementation work including features, testing results, technical decisions, and refactoring. |
||
|
Georgi Gerganov
|
23d4e21a81 |
examples: refactor test-simulator.sh for better readability
Extract repeating question string into TEST_QUESTION variable and create make_request() helper function to reduce code duplication. Add proper error handling for error responses. |
||
|
Georgi Gerganov
|
07d5e1e0ea |
examples: add llama-server simulator for testing eval scripts
Add a standalone Python script that simulates a llama-server HTTP endpoint for testing the eval script. The simulator: - Implements /v1/chat/completions endpoint with OpenAI-compatible format - Loads AIME dataset from HuggingFace with local caching - Uses Levenshtein distance for intelligent question matching - Supports configurable success rate for correct/wrong answer generation - Provides debug logging for troubleshooting Also includes test scripts and documentation for testing and understanding the simulator functionality. |
||
|
gatbontonpc
|
8839037528 | add checkpointing | ||
|
gatbontonpc
|
89cab3dbc5 | Add readme | ||
|
gatbontonpc
|
c2d83ca048 | multi source llama-eval | ||
|
gatbontonpc
|
c05df17ce3 | working llama-eval mc and math suite | ||
|
Daniel Bevenius
|
6ab881b7c3 |
model-conversion : add tensor-info.py utility (#18954)
This commit adds a new python script that can be used to print tensors
information from a tensor in a safetensors model.
The motivation for this is that during model conversion work it can
sometimes be useful to verify the shape of tensors in the original
model. While it is possible to print the tensors when loading the model
this can be slow when working with larger models.
With this script it is possible to quickly query tensor shapes.
Example usage:
```console
(venv) $ ./scripts/utils/tensor-info.py --help
usage: tensor-info.py [-h] [-m MODEL_PATH] [-l] [tensor_name]
Print tensor information from a safetensors model
positional arguments:
tensor_name Name of the tensor to inspect
options:
-h, --help show this help message and exit
-m MODEL_PATH, --model-path MODEL_PATH
Path to the model directory (default: MODEL_PATH environment variable)
-l, --list List unique tensor patterns in the model (layer numbers replaced with #)
```
Listing tensor names:
```console
(venv) $ ./scripts/utils/tensor-info.py -m ~/work/ai/models/google/embeddinggemma-300m -l
embed_tokens.weight
layers.#.input_layernorm.weight
layers.#.mlp.down_proj.weight
layers.#.mlp.gate_proj.weight
layers.#.mlp.up_proj.weight
layers.#.post_attention_layernorm.weight
layers.#.post_feedforward_layernorm.weight
layers.#.pre_feedforward_layernorm.weight
layers.#.self_attn.k_norm.weight
layers.#.self_attn.k_proj.weight
layers.#.self_attn.o_proj.weight
layers.#.self_attn.q_norm.weight
layers.#.self_attn.q_proj.weight
layers.#.self_attn.v_proj.weight
norm.weight
```
Printing a specific tensor's information:
```console
(venv) $ ./scripts/utils/tensor-info.py -m ~/work/ai/models/google/embeddinggemma-300m layers.0.input_layernorm.weight
Tensor: layers.0.input_layernorm.weight
File: model.safetensors
Shape: [768]
```
|
||
|
Daniel Bevenius
|
6156ae5111 |
model-conversion : add debug option to conversion script (#19265)
This commit adds a debug option to the model conversion script to enable using the Python debugger (pdb) during model conversion. The motivation for this is that I've found myself adding this a few times now and it would be quicker to have this flag as an option and a makefile target/recipe for it. |
||
|
Christian Kastner
|
7a4ca3cbd9 |
docs : Minor cleanups (#19252)
* Update old URLs to github.com/ggml-org/ * Bump copyrights |
||
|
Neo Zhang
|
2634ed207a | create test.sh to enhance the parameters for testing, update the guide, rm useless script (#19243) | ||
|
Daniele Pinna
|
1488339138 |
lookup, lookahead: fix crash when n_ctx not specified (#18729)
* lookup, lookahead: fix crash when n_ctx not specified Since PR #16653 (Dec 15, 2025), the default n_ctx is 0 to enable automatic GPU memory fitting. This causes llama-lookup and llama-lookahead to crash when run without explicit -c flag: GGML_ASSERT(batch.seq_id[batch.n_tokens] && "llama_batch size exceeded") Root cause: Both examples use params.n_ctx directly for batch initialization, but params.n_ctx remains 0 even after the context is properly initialized to n_ctx_train internally. Bug history: - Nov 2023: lookahead.cpp created (PR #4207) with params.n_ctx pattern - Dec 2023: lookup.cpp created (PR #4484) with same pattern - Nov 2024: default n_ctx changed to 4096 (PR #10136) - bug dormant - Dec 2025: default n_ctx changed to 0 (PR #16653) - bug activated The bug was dormant for 2+ years because params.n_ctx defaulted to 512, then 4096. PR #16653 changed it to 0 for GPU auto-fitting, triggering the crash. Fix: Use llama_n_ctx(ctx) to get the actual runtime context size, matching the pattern already used elsewhere in lookup.cpp (line 72) and in speculative.cpp/speculative-simple.cpp. Tested: llama-lookup now works without -c flag (12.5% acceptance on Gemma-3-1B). Note: llama-lookahead has a separate pre-existing issue with sequence initialization (n_seq_max=1 vs W+G+1 needed) that is unrelated to this fix. * lookahead: fix n_seq_max and kv_unified configuration Lookahead decoding requires: - W + G + 1 = 31 sequences for parallel Jacobi decoding - Unified KV cache for coupled sequences in batch splitting These requirements were broken after PR #14482 changed validation logic. Consolidates fix from PR #18730 per maintainer request. Commit message drafted with Claude. |
||
|
Sascha Rogmann
|
72d3b1898a |
spec : add self‑speculative decoding (no draft model required) + refactor (#18471)
* server: introduce self-speculative decoding * server: moved self-call into speculative.cpp * can_speculate() includes self-speculation Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * server: can_speculate() tests self-spec * server: replace can_speculate() with slot.can_speculate() Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * common: use %zu format specifier for size_t in logging Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * server: can_speculate() requires a task instance * common: ngram map, config self-speculative decoding * common: add enum common_speculative_type * common: add vector of speculative states * common: add option --spec-draftless * server: cleanup (remove slot.batch_spec, rename) * common: moved self-spec impl to ngram-map * common: cleanup (use common_speculative_state_draft) * spec : refactor * cont : naming * spec: remove --spec-config * doc: (draftless) speculative decoding * common: print performance in spec decoding * minor : cleanup * common : better names * minor : cleanup + fix build * minor: comments * CODEOWNERS: add common/ngram-map.* (#18471) * common : rename speculative.draftless_type -> speculative.type * ngram-map : fix uninitialized values * ngram-map : take into account the input can become shorter * ngram-map : revert len check for now * arg : change `--spec-draftless` -> `--spec-type` * spec : add common_speculative_state::accept() * spec : refactor + add common_speculative_begin() * spec : fix begin() call with mtmd * spec : additional refactor + remove common_speculative_params --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> |
||
|
Daniel Bevenius
|
a14b960bc7 |
model-conversion : use BUILD_DIR variable in all scripts (#19015)
This commit modifies all the utility scripts to use an optional
BUILD_DIR variable/argument to specify the build directory.
The motivation for this is that Commit
|
||
|
Daniel Bevenius
|
3d55846a5c |
model-conversion : add BUILD_DIR variable to run-converted-model scripts (#18927)
This commit adds a BUILD_DIR variable to the scripts used for running converted models. The motivation for this is that currently the `build` directory is hardcoded and it can be useful to specify a different build directory, with builds for different configurations. |
||
|
Georgi Gerganov
|
39173bcacb |
context : reserve new scheduler when graph topology changes (#18547)
* context : reserve new scheduler when graph topology changes * cont : fix * cont : fix reserve * cont : reserve only when changes occur + timing * context : add comments * llama : reserve on sampler changes * common : allow null common_sampler * server : task declares needs (embd, logits, sampling) * server : do not init sampler if not needed * llama : fix need_reserve when unsetting a sampler * server : consolidate slot reset/clear logic |
||
|
Adrien Gallouët
|
ec997b4f2b |
tests : download models only when running ctest (#18843)
Signed-off-by: Adrien Gallouët <angt@huggingface.co> |
||
|
Piotr Wilkin (ilintar)
|
d98b548120 |
Restore clip's cb() to its rightful glory - extract common debugging elements in llama (#17914)
* Extract common debugging functions; plug eval-callback and mtmd's MTMD_DEBUG_GRAPH with same functionality * Move to common * Remove unneeded header * Unlink from common * chore: update webui build output * Cleanup; properly pass params to mtmd without depending on common; factorize debug.cpp to use common debug code. * Revert change to webapp * Post-merge adjust * Apply suggestions from code review Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com> * Apply code review changes * Remove changes to server-context * Remove mtmd.h include * Remove utility functions from header * Apply suggestions from code review Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com> * Rename functions * Update tools/mtmd/clip.cpp Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com> * Update tools/mtmd/clip.cpp Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com> * Update tools/mtmd/clip.cpp Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com> --------- Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com> |
||
|
Adrien Gallouët
|
516a4ca9b5 | refactor : remove libcurl, use OpenSSL when available (#18828) | ||
|
Adrien Gallouët
|
f709c7a33f |
ci, tests : use cmake to download models and remove libcurl dependency (#18791)
* ci, tests : use cmake to download models and remove libcurl dependency * llama_dl_model -> llama_download_model * use EXPECTED_HASH for robust model downloading * Move llama_download_model to cmake/common.cmake Signed-off-by: Adrien Gallouët <angt@huggingface.co> |
||
|
Daniel Bevenius
|
20ca2e12c4 |
model-conversion : remove -c 0 from model card template [no ci] (#18807)
This commit removes the `-c, --ctx-size N` from the llama-server command in the model card template for causal models. The motivation for this is that -c 0 is the default and specifying it is redundant. |
||
|
Daniel Bevenius
|
4150da9a95 |
examples : add --kv-unified to batched example (#18774)
This commit adds the --kv-unified flag to the batched example. This flag is currently specified in the README.md as required, but is currently not available as a command line option for the batched example. The motivation for this is that specifying this flag as the README instructs, will lead to an error about the flag not being recognized, and without this option the example fail with the following error: ```console split_equal: sequential split is not supported when there are coupled sequences in the input batch (you may need to use the -kvu flag) decode: failed to find a memory slot for batch of size 4 main: llama_decode() failed ``` |
||
|
Daniel Bevenius
|
9789e28459 |
debug : include LLAMA_POOLING_TYPE_UNSPECIFIED in pooling check (#18692)
* debug : include LLAMA_POOLING_TYPE_UNSPECIFIED in pooling check This commit updates the pooling check in the debug example to also include LLAMA_POOLING_TYPE_UNSPECIFIED and not just LLAMA_POOLING_TYPE_NONE. * debug : normalize both pooled and token embeddings This commit updates debug.cpp to normalize embeddings for both pooled and non-pooled outputs. For pooled embeddings, normalization is applied to the single vector, and for non-pooled embeddings, normalization is applied to each token embedding vector individually. The motivation for this is to enable non-pooled embeddings to be normalized which was not possible previously. |
||
|
Daniel Bevenius
|
9c142e3a2a |
model-conversion : add warn about transformers mismatch (#18691)
This commit adds a check comparing the installed transformers library with the transformers version that the original model supports. This check will be performed upon a model verification failure and prints a warning/hint to the user suggesting to install the correct version of the transformers library. The motivation for this change is that it is possible for the model verification to fail due to differences in the transformers library used and it might not be obvious that this could be the cause of the failure. With this warning the correct version can be checked and hopefully save time troubleshooting the cause of the verification failure. |
||
|
Daniel Bevenius
|
df7fb92170 |
model-conversion : remove -st targets for converted model (#18689)
This commit removes the '-st` make target for running the converted embedding model. The motivation for this is that the pooling type is now part of the .gguf metdata of the model and this is used by llama-debug when running the model. So there is no need to specify the pooling type separately any more. The commit also adds an option to specify the type of normalization applied to the output embeddings when running the converted model. And the readme documentation has been updated to reflect these changes. |
||
|
Julius Tischbein
|
2038101bd9 |
llama : add use_direct_io flag for model loading (#18166)
* Adding --direct-io flag for model loading * Fixing read_raw() calls * Fixing Windows read_raw_at * Changing type off_t to size_t for windows and Renaming functions * disable direct io when mmap is explicitly enabled * Use read_raw_unsafe when upload_backend is available, not functional on some devices with Vulkan and SYCL * Fallback to std::fread in case O_DIRECT fails due to bad address * Windows: remove const keywords and unused functions * Update src/llama-mmap.cpp Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> --------- Co-authored-by: jtischbein <jtischbein@gmail.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> |
||
|
Daniel Bevenius
|
ffba4f29e6 |
examples : add debug utility/example (#18464)
* examples : add debug utility/example
This commit introduces a new example named llama-debug which is a
utility that is intended to be used to assist with developing/debugging
a converted model.
The motivation for this utilitiy is to assist in model conversion work
to verify that the model produces the expected outputs. It is intended
to replace logits.cpp in examples/model-conversion.
Example usage:
```console
./build/bin/llama-debug \
-m models/Qwen2.5-0.5B-Instruct.gguf \
--prompt "Hello, my name is" \
--save-logits
...
Model add_bos: false
Input prompt: "Hello, my name is"
Token ids (5):
Hello(9707) ,(11) my(847) name(829) is(374)
Data saved to data/llamacpp-Qwen2.5-0.5B-Instruct.bin
Data saved to data/llamacpp-Qwen2.5-0.5B-Instruct.txt
Prompt saved to data/llamacpp-Qwen2.5-0.5B-Instruct-prompt.txt
Tokens saved to data/llamacpp-Qwen2.5-0.5B-Instruct-tokens.bin
```
For more details about the options available for this example, please
refer to examples/debug/README.md.
* throw runtime error instead of logging error
* remove params.warmup and enable the warmup/nowarmup option
* model-conversion : remove logits.cpp
This commit removes logits.cpp in favor of using llama-debug for
generating logits and embeddings.
* examples : remove model-conversion directory
This was missed in the previous commit.
* model-conversion : add support for saving prompt and token ids
This commit add support for storing the prompt and the token ids for the
prompt when running the original models.
The motivation for this is that this will allow us to compare the prompt
and the tokens generated for the prompt when verifing the converted
model. Currently it is possible that even if the same prompt is used
that the tokens generated are different if there is a difference in the
tokenization between the original and converted model which would
currently go unnoticed (the verification will most likely fail but it
might not be obvious why).
* squash! model-conversion : add support for saving prompt and token ids
fix pyright errors.
* model-conversion : add compare_tokens utility
This commit adds a script to compare token outputs between original and
converted models.
Example usage:
```console
(venv) $ ./scripts/utils/compare_tokens.py pytorch-gemma-3-270m-it llamacpp-gemma-3-270m-it-bf16
Comparing tokens between:
Original : pytorch-gemma-3-270m-it (6 tokens)
Converted: llamacpp-gemma-3-270m-it-bf16 (6 tokens)
✅ All 6 tokens match!
```
And there is a verbose flag that will also print out the prompts:
```console
(venv) $ ./scripts/utils/compare_tokens.py pytorch-gemma-3-270m-it llamacpp-gemma-3-270m-it-bf16 -v
Original model prompt (pytorch-gemma-3-270m-it):
prompt: Hello, my name is
n_tokens: 6
token ids: 2, 9259, 236764, 1041, 1463, 563
Converted model prompt (llamacpp-gemma-3-270m-it-bf16):
prompt: Hello, my name is
n_tokens: 6
token ids: 2, 9259, 236764, 1041, 1463, 563
Comparing tokens between:
Original : pytorch-gemma-3-270m-it (6 tokens)
Converted: llamacpp-gemma-3-270m-it-bf16 (6 tokens)
✅ All 6 tokens match!
```
* model-conversion : add token comparison to verifiction scripts
This commit add the calling of the compare_tokens function in
compare-logits.py and semantic_check.py to ensure that the token ids
that the tokenizers procoduce are the same before proceeding with
verifying the logits/embeddings.
Placing them in the existing scripts instead calling them separately
ensures that the token comparison is always done prior to the
logit/embedding verifications.
Follow up commit/pr could refactor the causal logits verification into
a single script instead of the two that exist now. This would reduce the
code and make it consistent with the embeddings verficiation which only
has a single script.
* debug : use llama_model_n_embd_out
This commit updates the debug example to use the new function
llama_model_n_embd_out instead of llama_model_n_embd.
The motivation for this change is to support late interation retriever
models, like LFM2-ColBert-350M, where the output embeddings are down
projected to a lower dimension.
* debug : add print_usage function
This commit adds a print_usage function that is passed to the
common_params_parse.
The motivation for this is that this enables a specific usage message
which will be printed after all the options, for example:
```console
example usage:
Print tensors:
./build/bin/llama-debug -m model.gguf -p "Hello my name is" --verbose
The tensors to be printed can be filtered with --tensor-filter option.
Save logits/embeddings:
./build/bin/llama-debug -m model.gguf -p "Hello my name is" --save-logits
Add --embedding to save embeddings
```
|
||
|
Tarek Dakhran
|
73d284a250 |
model : add LFM2-ColBert-350M (#18607)
* model : add LFM2-ColBert-350M * llama_model_n_embd_out() - returns `hparams.n_embd_out` if set and fallbacks to `hparams.n_embd` |
||
|
Daniel Bevenius
|
d3dce4e0a5 |
sampling : add support for backend sampling (#17004)
* sampling : add support for backend sampling This commit adds support for performing sampling operations on the backend (e.g. GPU) as part of the model computation graph. The motivation for this feature is to enable sampling to be performed directly on the backend as part of the computation graph being executed, allowing for some or all of the sampling to be done on the backend. For example, the backend sampler chain might select/sample a token directly in which case only the sampled token needs to be transferred from device memory to host memory. It is also possible for the backend samplers to perform filtering of the logits, or compute and filter the probability distribution, in which case only the filtered logits or probabilites need to be transferred back to system memory for further processing by CPU samplers. Currently the backend sampling works in a similar manner to how pooling works, it is a function that is called by build_graph and the sampler operations become part of the models computation graph. * llama-cli : add backend sampler configuration * server : add backend sampling options/configuration * webui : add backend sampling options * ggml : add initial cumsum implementation for CUDA * sampling : enable all backend sampler tests This commit enables all exisiting backend sampler tests in the test-backend-sampler. Previously, some tests were disabled because there were missing ggml operation implementations. * graph : do not include llama-model.h * sampling : always expose sampled_ids This commit precomputes and caches the full-vocab token id list in llama_context's constructor, so llama_get_backend_sampled_token_ids_ith always returns a valid pointer. The motivation for this is that this enables both common/sampling.cpp and src/llama-sampling.cpp can simplify their logic. Not all backends samplers that process logits need to set the sampled_tokens_id as they may not change the order of the logits, for example the temperature sampler only scales the logits but does not change their order. Simliar the logit bias sampler only adds bias to specific token ids but does not change the order of the logits. In these cases there will not be a device to host copy of the sampled token ids, and this is the use case where having this precomputed list is useful. * sampling : ensure at most one output token per seq This commit adds a check in the batch allocator to ensure that when backend sampling is enabled, at most one output token is specified per sequence. * CUDA: Optimize argsort for gpu-based token sampling Argsort is used for top-k currently. WE optimize argsort by 2 things: 1. Use `DeviceRadixSort` for single-row/sequence to parallelize it across our SMs 2. Use `DeviceSegmentedSort` for multi-row/sequence as this is the correct entrypoint (the function chooses different execution paths, it contains `DeviceSegmentedRadixSort` as one of the paths and will choose the best one according to heuristics. https://nvidia.github.io/cccl/cub/api/structcub_1_1DeviceSegmentedSort.html#overview Some perf numbers for a RTX PRO 6000: On the kernel level, tested with `GGML_CUDA_DISABLE_GRAPHS=1 ./test-backend-ops -o ARGSORT perf` Before: ``` ARGSORT(type=f32,ne=[65000,16,1,1],order=0): 4130 runs - 359.24 us/run ARGSORT(type=f32,ne=[200000,1,1,1],order=0): 8192 runs - 861.34 us/run ARGSORT(type=f32,ne=[200000,16,1,1],order=0): 1343 runs - 1020.01 us/run ``` After: ``` ARGSORT(type=f32,ne=[65000,16,1,1],order=0): 4130 runs - 312.41 us/run ARGSORT(type=f32,ne=[200000,1,1,1],order=0): 16384 runs - 63.48 us/run ARGSORT(type=f32,ne=[200000,16,1,1],order=0): 1343 runs - 874.36 us/run ``` --- On the model level, tested with `llama-cli -m gpt-oss-20b-mxfp4.gguf -n 200 -p "What is the Capital of Sweden?" -no-cnv -fa 1 --backend-sampling` Before: ``` llama_perf_sampler_print: sampling time = 0.25 ms / 207 runs ( 0.00 ms per token, 824701.20 tokens per second) llama_perf_context_print: load time = 18215.58 ms llama_perf_context_print: prompt eval time = 28.20 ms / 7 tokens ( 4.03 ms per token, 248.19 tokens per second) llama_perf_context_print: eval time = 714.79 ms / 199 runs ( 3.59 ms per token, 278.40 tokens per second) llama_perf_context_print: total time = 857.62 ms / 206 tokens ``` After ``` llama_perf_sampler_print: sampling time = 0.25 ms / 207 runs ( 0.00 ms per token, 828000.00 tokens per second) llama_perf_context_print: load time = 18366.92 ms llama_perf_context_print: prompt eval time = 35.92 ms / 7 tokens ( 5.13 ms per token, 194.87 tokens per second) llama_perf_context_print: eval time = 532.79 ms / 199 runs ( 2.68 ms per token, 373.50 tokens per second) llama_perf_context_print: total time = 683.65 ms / 206 tokens ``` * sampling : remove version from sampler chain This commit removes the version field from the sampler chain and instead used the sampler pointer itself for change detection. * sampling : always populate logits for sampled probs This commit updates common/sampler.cpp set_logits and src/llama-sampling.cpp llama_sampler_sample to always populate the logits field when backend sampled probabilities are available. The motivation for this is that this ensure that CPU sampler always have access to the logits values even when probabilites have been produced by backend samplers. * sampling : simplify backend sampling logic decode This commit tries to simplify the backend sampling logic in llama_context::decode. * squash! sampling : simplify backend sampling logic decode Fix condition to check if backend actually sampled tokens, not just that backend samplers are available. * common : fix regression caused by extra memory allocations during sampling * squash! sampling : simplify backend sampling logic decode The commit fixes a variable shadowing issue in the `llama_context::decode` function which was introduced in a previous refactoring. * squash! common : fix regression caused by extra memory allocations during sampling Apply the same changes to llama-sampling.cpp, llama_sampler_sample as were applied in commit |
||
|
Daniel Bevenius
|
a864fb1c14 |
model-conversion : use CONVERTED_MODEL for compare-embeddings (#18461)
This commit updates the causal model verification script to use the
CONVERTED_MODEL environment variable instead of using the MODEL_PATH
(the original model path) as the basis for the converted model file
name.
The motivation for this that currently if the converted model file name
differs from the original model directory/name the verification script
will look for the wrong .bin file that was generating when running
the converted model.
This similar to the change made for the embeddings models script in
Commit
|
||
|
Naco Siren
|
c1366056f6 |
android: routine maintenance - Dec 2025 (#18338)
* Fix `msg` typo * Fix thread safety in destroy() to support generation abortion in lifecycle callbacks. * UI polish: stack new message change from below; fix GGUF margin not in view port * Bug fixes: rare racing condition when main thread updating view and and default thread updating messages at the same time; user input not disabled during generation. * Bump dependencies' versions; Deprecated outdated dsl usage. |
||
|
Daniel Bevenius
|
7cbec34a63 |
model-conversion : add device option to embd run orig model (#18386)
This commit refactors the original model embedding script to include a device selection option. Users can now specify the device (cpu, cuda, mps, auto) via command-line arguments. It also refactors the code to be more structured. |