llama-perplexity -hf unsloth/Qwen3-0.6B-GGUF:Q4_K_M -f winogrande-debiased-eval.csv --winogrande
winogrande_score : tokenizing selected tasks
winogrande_score : calculating winogrande score over selected tasks.
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 46
failed to decode the batch, n_batch = 2048, ret = 1
winogrande_score: llama_decode() failed
same for hellaswag:
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 99
failed to decode the batch, n_batch = 2048, ret = 1
hellaswag_score: llama_decode() failed
Signed-off-by: Adrien Gallouët <angt@huggingface.co>
* llama : fix pooling assertion crash in chunked GDN detection path
The chunked fused Gated Delta Net detection in sched_reserve() calls
graph_reserve(16*n_seqs, n_seqs, n_outputs, ...) where n_outputs = n_seqs.
This creates a dimension mismatch in build_pooling() for embedding models
with mean/rank pooling: build_inp_mean() creates a tensor with shape
[n_tokens=16*n_seqs, ...] while t_embd is reduced to [n_outputs=n_seqs, ...]
via out_ids, causing ggml_mul_mat to assert on ggml_can_mul_mat(a, b).
Fix: pass n_tokens as n_outputs in the chunked GDN graph reservation,
matching the pattern used by the pp/tg worst-case reservations.
Regression introduced by #20340 (d28961d).
Same class of bug as #12517, fixed by #12545.
* server : add mean pooling tests to embedding test suite
Add test_embedding_pooling_mean and test_embedding_pooling_mean_multiple
to cover the --pooling mean codepath, which was previously untested.
These tests would have caught the regression introduced by #20340 where
build_pooling() crashes with a ggml_mul_mat assertion due to mismatched
dimensions in the chunked GDN detection path.
---------
Co-authored-by: Domenico Crupi <domenico@zerovolt.it>
* server: reset kill-switch on client error
This avoids triggering a server kill switch.
If the client sends a request that exceeds the configured context size, an appropriate HTTP 400 response is provided and no tokens are generated.
However since no tokens are generated, update_slots() increments n_empty_consecutive. If the client sends 3 such messages in a row, the server terminates.
* moved counter reset as per recommendation
* cont : minor
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit renames the the function `mtmd_get_audio_bitrate` to
`mtmd_get_audio_sample_rate` to better reflect its purpose.
The motivation for this is that the function currently returns the audio
sample rate, not the bitrate (sample_rate × bit_depth × channels), and
that is how it is used in the code as well.
This is a breaking change, but I believe mtmd is still in
experimental/development phase so it might be alright to simply rename.
* quantize : imatrix-fail early + code cleanup
* fix manual override printing
it's in the preliminary loop now, so needs to be on its own line
* revert header changes per ggerganov
* remove old #includes
* clarify naming
rename `tensor_quantization` to `tensor_typo_option` to descirbe its
functionality
* fix per barto
* Parse port numbers from MCP server URLs
* Pass scheme to http proxy for determining whether to use SSL
* Fix download on non-standard port and re-add port to logging
* add test
---------
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
* tests: add end-to-end tests per model architecture
* fixup for rebase
* fix use-after-free in llama-model-loader.cpp
* fix CI
* fix WebGPU
* fix CI
* disable CI for macOS-latest-cmake-arm64
* use expert_weights_scale only if != 0.0f
* comments
* Set C locale for consistent float formatting across all binaries.
* Add C locale setting to all tools binaries
Add std::setlocale(LC_NUMERIC, "C") to all 16 binaries in the tools/
directory to ensure consistent floating-point formatting.
* Apply suggestion from @JohannesGaessler
---------
Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
* server : support multiple model aliases via comma-separated --alias
* server : update --alias description and regenerate docs
* server : multiple model aliases and tags
- address review feedback from ngxson
- --alias accepts comma-separated values (std::set, no duplicates)
- --tags for informational metadata (not used for routing)
- aliases resolve transparently in router via get_meta/has_model
- /v1/models exposes aliases and tags fields
* regenerate docs
* nits
* server : use first alias as model_name for backward compat
address review feedback from ngxson
* server : add single-model test for aliases and tags
* WIP: Add EuroBERT support with autoformatting changes
This commit includes:
- EuroBERT model implementation for GGUF conversion
- C++ backend support for EuroBERT architecture
- Unintended autoformatting changes to Python files
Saving before reverting formatting-only changes.
* feat: add back eos assert when not last token pooling
* feat: removed duplicated code and cleanup
* feat: removed not working architectures and unnecessary check
* fix: typo
* fix: dynamic pooling config
* feat: added an example model for eurobert
* feat: proper llama-vocab implementation for jina-v5
* fix: removed unnecessary comments
* server: fix query params lost when proxying requests in multi-model router mode
* server: re-encode query params using httplib::encode_query_component in proxy
* llama : remove write/read of output ids/logits/embeddings
This commit removes the write/read of output ids, logits and
embeddings from the llama context state.
Refs: https://github.com/ggml-org/llama.cpp/pull/18862#issuecomment-3756330941
* completion : add replying of session state
This commit updates the session handing in the completion tool to handle
the that logits are no longer stored in the session file. Instead, we
need to replay the last token to get the logits for sampling.
* common : add common_prompt_batch_decode function
This commit adds a new function which is responsible for decoding prompt
and optionally handle the saving for session data.
* update save-state.cpp to use llama_state_load_file
This commit updates the save-load-state example to utilize the new
llama_state_load_file function for loading the model state from a file.
And it also replays the last token after loading since this state is now
stored before the last token is processed.
* examples : set n_seq_max = 2 for ctx3
This commit updates the save-load-state example to set the n_seq_max
parameter to 2 when initializing the ctx3 context.
The motivation for this change is that using 1 as n_parallel/n_seq_max
the context only supports one sequence, but the test laster tries to
use a second sequence which results in the following error:
```console
main : loaded state with 4 tokens
main : seq 0 copied, 225760 bytes
main : kv cache cleared
find_slot: seq_id=1 >= n_seq_max=1 Try using a bigger --parallel value
state_read_meta: failed to find available cells in kv cache
```
This seems to only happen for recurrent/hybrid models.
* mtmd : chat : Fix extra \n between text and media marker
Thanks to @tugot17 for detecting and reporting the issue.
For vision models (e.g. LFM2.5-VL-1.6B and Qwen/Qwen3-VL-4B-Instruct) `llama-mtmd-cli` produces identical output to HF implementation.
However `llama-server` doesn't. I traced it down to extra newline
inserted after `<__media__>`.
This happens in `to_json_oaicompat`, that treats media markers as text
and joins all parts with `\n` separator.
PR introduces new type `media_marker` and uses it for media markers.
Extra logic is added to prevent insertion of newlines before and after
media markers.
With this change number of input tokens is identical to HF
implementation and as a result the output is also identical.
I explored other ways to address the issue
* remove completely `\n` between text parts in `to_json_oaicompat`
* merge text messages in server-common.cpp before sending them to `to_json_oaicompat`
Please propose alternative ways of fixing this issue.
* Refactor to use explicite per type ifs
* Update common/chat.cpp
Co-authored-by: Piotr Wilkin (ilintar) <piotr.wilkin@syndatis.com>
* Update common_chat_templates_apply_legacy
---------
Co-authored-by: Piotr Wilkin (ilintar) <piotr.wilkin@syndatis.com>
* save generated text for the /slots endpoint
* update debug_generated_text only when LLAMA_SERVER_SLOTS_DEBUG > 0
* Apply suggestions from code review
---------
Co-authored-by: Matteo <matteo@matteo>
Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>
This option was introduced as a workaround because cpp-httplib could not
build on visionOS. Since it has been fixed and now compiles on all platforms,
we can remove it and simplify many things.
Signed-off-by: Adrien Gallouët <angt@huggingface.co>
* feat: Enable adding System Prompt per-chat
* fix: Save draft message in Chat Form when adding System Prompt from new chat view
* fix: Proper system message deletion logic
* chore: Formatting
* chore: update webui build output
* Move dequant_model to after the text_config merge
Add new kimi-k2.5 keys to mtmd convert
Update V_MMPROJ tensor mapping for new mm_projector.proj keys
Update V_M_IMP_NORM for new mm_projector.pre_norm key
* Fix a couple of oversights
* Add image support for Kimi-K2.5
* Revert changes to KimiVLForConditionalGeneration
* Fix an assert crash
* Fix permute swapping w / h on accident
* Kimi-K2.5: Use merged QKV for vision
* Kimi-K2.5: pre-convert vision QK to use build_rope_2d
* Kimi-K2.5: support non-interleaved rope for vision
* Kimi-K2.5: fix min / max pixel
* Kimi-K2.5: remove v/o permutes, unnecessary
* Kimi-K2.5: update permute name to match
* Update convert_hf_to_gguf.py
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* Kimi-K2.5: replace build_rope_2d ggml_cont with ggml_view_3d pointers
---------
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
* support qwen3.5 series
* remove deepstack for now, and some code clean
* code clean
* add FULL_ATTENTION_INTERVAL metadata
* code clean
* reorder v heads for linear attention to avoid expensive interleaved repeat
* completion : simplify batch (embd) processing
This commit simplifies the processing of embd by removing the for loop
that currently exists which uses params.n_batch as its increment. This
commit also removes the clamping of n_eval as the size of embd is always
at most the size of params.n_batch.
The motivation is to clarify the code as it is currently a little
confusing when looking at this for loop in isolation and thinking that
it can process multiple batches.
* add an assert to verify n_eval is not greater than n_batch
Experimenting with AI, my environment gets messy fast and it's not
always easy to know what model my software is trying to load. This helps
with troubleshooting.
before:
Error: {
code = 400,
message = "model not found",
type = "invalid_request_error"
}
After:
Error: {
code = 400,
message = "model 'toto' not found",
type = "invalid_request_error"
}
* add option --tensor-type-file to llama-quantize, but it raises an error.
* add error message when file not found
* quantize: update help menu, fix CI
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
---------
Signed-off-by: Aaron Teo <aaron.teo1@ibm.com>
Co-authored-by: Your Name <you@example.com>
Co-authored-by: Aaron Teo <aaron.teo1@ibm.com>
* common : use two decimal places for float arg help messages
This commit updates the help messages for various command-line arguments
in arg.cpp to display floating-point default values with two decimal
places instead of one.
The motivation for this changes is that currently only having one decimal
place means that values generated using --help or llama-gen-docs will not
display the correct values.
For example, currently the value of top-p in tools/server/README.md is
`0.9`, but the default value is actually '0.95'. And running
llama-gen-docs does not update this value as it uses the output from the
help message, which shows only one decimal place, so the values look
like they are unchanged.
* docs : run llama-gen-docs to update docs
Chedrian07
Adrien Gallouët
ZeroV0LT
SoftwareRenderer
Daniel Bevenius
Piotr Wilkin (ilintar)
Pascal
DAN™
Georgi Gerganov
ddh0
Evan Huus
Aaron Teo
Johannes Gäßler
decahedron1
Tom Vaucourt
Aleksander Grygier
Roj234
Sigbjørn Skjæret
Marcel Petrick
SamareshSingh
standby24x7
Sami Kama
drrros
Maximilian Werk
yggdrasil75
Radoslav Gerganov
Kilian Krampf
Aldehir Rojas
crsawyer
ddh0
megemini
Saba Fallah
Tarek Dakhran
matteo
Xuan-Son Nguyen
AesSedai
Anav Prasad
iMil
RichardScottOZ
JJJYmmm
손희준
Sascha Rogmann
Matthieu Coudron
Christian Kastner
EugeoSynthesisThirtyTwo
tc-mb
Andrew Marshall