Fix qwen reasoning tool calling required #3

ExtReMLapin · 2025-09-01T07:24:24Z

Make sure to read the contributing guidelines before submitting a PR

…equired

…already opened grammar)

…r accepting piece:`

…it, just disable it, don't GGML_ABORT

… it's own issue

…rg#15622) Prior to this change, we faced undefined cublasLt references when attempting to compile 'llama-cli' with GGML_STATIC=ON on Linux. We add linking with CUDA::cublasLt_static when CUDA version is greater than 10.1.

This commit adds a new target to the Makefile for converting models that are multimodal. This target will convert the original model and in addition also create the mmproj GGUF model. The motivation for this change is that for models that are multimodal, for example those that contain a vision encoders, we will often want to upload both the quantized model and the vision encoder model to HuggingFace. Example usage: ```console $ make causal-convert-mm-model MODEL_PATH=~/work/ai/models/gemma-3-4b-it-qat-q4_0-unquantized/ ... The environment variable CONVERTED_MODEL can be set to this path using: export CONVERTED_MODEL=/home/danbev/work/ai/llama.cpp/models/gemma-3-4b-it-qat-q4_0-unquantized.gguf The mmproj model was created in /home/danbev/work/ai/llama.cpp/models/mmproj-gemma-3-4b-it-qat-q4_0-unquantized.gguf ``` The converted original model can then be quantized, and after that both the quantized model and the mmproj file can then be uploaded to HuggingFace. Refs: https://huggingface.co/ggml-org/gemma-3-4b-it-qat-GGUF/tree/main

…15604) * Change to warn instead of debug, to explain reason for stopping. * Update tools/main/main.cpp Fix printing --2 Co-authored-by: Georgi Gerganov <[email protected]> --------- Co-authored-by: Georgi Gerganov <[email protected]>

* gguf-py: implement byteswapping for Q4_0 This is needed to byteswap Mistral model. Also restore original shapes after byteswapping tensors. It is not needed at the moment, but do it in case they'd be used in future. * Rework byteswapping code in gguf-py Move out details from byteswapping tensor blocks code

ggml-ci

* initial jina-embeddings-v3 support * initial jina-embeddings-v3 support * initial jina-embeddings-v3 support * fix vocab parsing with only tokenizer.json * set mask token lstrip attribute * additional unk_token_id fallback just in case [no ci] * revert vocab_size() change [no ci] * merge tensor loading into general bert * rope * add lora embedding and loading (non-functional) * export separate lora ggufs instead * add adapter metadata api * use std::string * convert_hf_to_lora compatibility * fix assert * apply suggestions from review * apply suggestion from review

…15638) ggml-ci

Signed-off-by: Aaron Teo <[email protected]>

* CUDA: add conv2d * CUDA: conv2d - correct formatting and added const

…equired

… printed values (ggml-org#15637) This makes it much easier to compare between llama.cpp and transformers! https://github.com/ggml-org/llama.cpp/issues/nemotron-nano-15409 Branch: gabe-l-hart/nvidia-nemotron-nano-15409 Signed-off-by: Gabe Goodhart <[email protected]>

* feat: Add NEMOTRONH to python arch enum https://github.com/ggml-org/llama.cpp/issues/nemotron-nano-15409 Branch: gabe-l-hart/nvidia-nemotron-nano-15409 Signed-off-by: Gabe Goodhart <[email protected]> * feat: Add NEMOTRONH to c++ arch enum https://github.com/ggml-org/llama.cpp/issues/nemotron-nano-15409 Branch: gabe-l-hart/nvidia-nemotron-nano-15409 Signed-off-by: Gabe Goodhart <[email protected]> * feat: Add NEMOTRONH to llama-arch layer map https://github.com/ggml-org/llama.cpp/issues/nemotron-nano-15409 Branch: gabe-l-hart/nvidia-nemotron-nano-15409 Signed-off-by: Gabe Goodhart <[email protected]> * feat: First pass at conversion for nemotronh https://github.com/ggml-org/llama.cpp/issues/nemotron-nano-15409 Branch: gabe-l-hart/nvidia-nemotron-nano-15409 Signed-off-by: Gabe Goodhart <[email protected]> * feat: Add a verbose log for each tensor loaded This is really helpful for diagnosing mismatches between the expected and received tensors https://github.com/ggml-org/llama.cpp/issues/nemotron-nano-15409 Branch: gabe-l-hart/nvidia-nemotron-nano-15409 Signed-off-by: Gabe Goodhart <[email protected]> * feat: First (broken) pass at nemotronh model architecture It generates tokens, just not valid ones! https://github.com/ggml-org/llama.cpp/issues/nemotron-nano-15409 Branch: gabe-l-hart/nvidia-nemotron-nano-15409 Signed-off-by: Gabe Goodhart <[email protected]> * fix: Explicitly enable add_bos_token during conversion The `tokenizer.json`/`tokenizer_config.json` in the model are a bit contradictory. In the config, add_bos_token is set to False, but the tokenizer model itself has a post_processor that adds the BOS token via type: TemplateProcessing https://github.com/ggml-org/llama.cpp/issues/nemotron-nano-15409 Branch: gabe-l-hart/nvidia-nemotron-nano-15409 Signed-off-by: Gabe Goodhart <[email protected]> * fix: Use relu2 (LLM_FFN_RELU_SQR) for activation in FFN layers https://github.com/ggml-org/llama.cpp/issues/nemotron-nano-15409 Branch: gabe-l-hart/nvidia-nemotron-nano-15409 Signed-off-by: Gabe Goodhart <[email protected]> * fix: Only allocate attention cache for attention layers (not non-recurrent) https://github.com/ggml-org/llama.cpp/issues/nemotron-nano-15409 Branch: gabe-l-hart/nvidia-nemotron-nano-15409 Signed-off-by: Gabe Goodhart <[email protected]> * fix: Move residual add to after every block https://github.com/ggml-org/llama.cpp/issues/nemotron-nano-15409 Branch: gabe-l-hart/nvidia-nemotron-nano-15409 Signed-off-by: Gabe Goodhart <[email protected]> * fix: Use the correct norm tensor for the MLP blocks https://github.com/ggml-org/llama.cpp/issues/nemotron-nano-15409 Branch: gabe-l-hart/nvidia-nemotron-nano-15409 Signed-off-by: Gabe Goodhart <[email protected]> * Nemotron-H: MLP gate cleanup (pass NULL for unused gate) This model does not use a gate in MLP blocks; pass NULLs for gate tensors to make intent clear and avoid unused-pointer noise. * SSM: respect ssm_dt_rank for dt_dim when provided Use GGUF-provided time_step_rank (ssm_dt_rank) to set dt_dim when > 0; fallback to max(64, n_embd/16). * fix: plamo2 - revert dt_dim to default (remove ssm_dt_rank usage) * Rename nemotronh to nemotron_h for consistency - Update architecture name from NEMOTRONH to NEMOTRON_H in constants.py - Change architecture string from 'nemotronh' to 'nemotron_h' in all files - Update enum LLM_ARCH_NEMOTRONH to LLM_ARCH_NEMOTRON_H - Update class name llm_build_nemotronh to llm_build_nemotron_h - Consistent naming with underscore convention (nemotron_h vs nemotronh) * feat: Support conversion for older NemotronH models https://github.com/ggml-org/llama.cpp/issues/nemotron-nano-15409 Branch: gabe-l-hart/nvidia-nemotron-nano-15409 Signed-off-by: Gabe Goodhart <[email protected]> --------- Signed-off-by: Gabe Goodhart <[email protected]> Co-authored-by: Maicon Domingues <[email protected]> Co-authored-by: weatherman <[email protected]>

* CUDA: fused add with rms_norm_mul * Non-broadcast fuse works * Add fused adds * format * Remove n_fuse from template params * Address review comments * Move template inside binbcast

* Reasoning and tool-calling support for Seed OSS * Fix grammar and partial parsing * Whitespace * New chat template * Update common/chat.cpp Co-authored-by: Sigbjørn Skjæret <[email protected]> * Update common/chat.cpp Co-authored-by: Sigbjørn Skjæret <[email protected]> * Remove unused 'purge_healing_marker' helper --------- Co-authored-by: Sigbjørn Skjæret <[email protected]>

…#15652) * vulkan: clamp matmul and FA results to the max finite value * only clamp for fp16

…#15649) * vulkan: Allow fallback to sysmem memory when vidmem is full * vulkan: Add env var GGML_VK_ALLOW_SYSMEM_FALLBACK

…#15679) This commit removes the portability_enumeration_ext variable from the ggml_vk_instance_portability_enumeration_ext_available function as it is initialized to false but never modified, making it redundant.

* vulkan: mul_mat_id coopmat2 optimizations Add a path for when the tile fits in BN/2, similar to what we have for mul_mat. Only call fetch_scales/store_scales once per QUANT_K block, and once at the beginning in case start_k is not aligned. * Also add a path for BN/4 - worth a couple more percent

) Exposes ggml_backend_sched_split_graph() to allow splitting the graph without allocating compute buffers and uses it to split the graph for the automatic Flash Attention check.

ggml-ci

* metal : fix checks for available FA kernels ggml-ci * cont : fix comment [no ci]

* server : enable /slots by default and make it secure ggml-ci * server : fix tests to pass `--no-slots` when necessary * server : extend /props with info about enabled endpoints

* sampling : optimize sorting using bucket sort in more places ggml-ci * sampling : do not sort in dist sampler ggml-ci * sampling : avoid heap allocations for sort buffers ggml-ci * common : add option to sort sampling candidates by probability ggml-ci * sampling : revert the change for preserving sort buffers * sampling : use std::copy instead of memcpy * sampling : clarify purpose of partial sort helpers ggml-ci * cont : remove wrong comment [no ci] * common : update comment Co-authored-by: Johannes Gäßler <[email protected]> --------- Co-authored-by: Johannes Gäßler <[email protected]>

* CANN: fix RoPE cache issue on multi-device RoPE cache only needs to be computed once per token. However, in multi-device scenarios, not every device starts computation from layer 0, which may lead to unallocated memory issues and precision errors. This commit records the first layer of each device to avoid the above issues. * CANN: Optimize first-layer detection method * CANN: Remove trailing whitespace * CANN: Only cache the data that can be determined as unchanged through the parameters. * CANN: Update function comment

…ml-org#15690) * CUDA: fix build error from ambiguous __half conversions in conv2d Building conv2d with half precision failed because `__half` defines multiple implicit conversion operators (to float, int, short, etc.), causing ambiguous overload resolution when multiplying with float. Introduce a templated `to_float` helper that explicitly converts `__half` via `__half2float`, while passing through float unchanged. Use this helper in conv2d accumulation to ensure unambiguous and correct promotion to float. Fixes some build errors with half-precision kernels on CUDA. ggml-ci * CUDA: Replace custom to_float helper with unified ggml_cuda_cast and add half‑>float conversion * CUDA: Add missing convert.cuh header * CUDA: remove unnecessary extension in ggml_cuda_cast * CUDA: Address review comment, remove second type template argument

…equired

…gml-org#16038) Initalizing RESERVED_NAME in is_reserved_name() is not thread safe and leads to corrupted memory when used from multiple threads as can be seen in the asan trace below. This fixes the initialization to make it thread-safe. #0 0x000100abd018 in std::__1::pair<std::__1::__hash_iterator<std::__1::__hash_node<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, void*>*>, bool> std::__1::__hash_table<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, std::__1::hash<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>>, std::__1::equal_to<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>>, std::__1::allocator<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>>>::__emplace_unique_key_args<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&>(std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&) __hash_table:1565 #1 0x000100ab0320 in SchemaConverter::visit(nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&) json-schema-to-grammar.cpp:802 #2 0x000100aafc48 in std::__1::__function::__func<build_grammar(std::__1::function<void (common_grammar_builder const&)> const&, common_grammar_options const&)::$_2, std::__1::allocator<build_grammar(std::__1::function<void (common_grammar_builder const&)> const&, common_grammar_options const&)::$_2>, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> (std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&, nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&)>::operator()(std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&, nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&) function.h:319 #3 0x000100a2c938 in std::__1::__function::__func<common_chat_params_init_llama_3_x(minja::chat_template const&, templates_params const&, bool)::$_0::operator()(common_grammar_builder const&) const::'lambda'(nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&), std::__1::allocator<common_chat_params_init_llama_3_x(minja::chat_template const&, templates_params const&, bool)::$_0::operator()(common_grammar_builder const&) const::'lambda'(nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&)>, void (nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&)>::operator()(nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&) function.h:319 #4 0x000100a139f8 in foreach_function(nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&, std::__1::function<void (nlohmann::json_abi_v3_12_0::basic_json<nlohmann::json_abi_v3_12_0::ordered_map, std::__1::vector, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, bool, long long, unsigned long long, double, std::__1::allocator, nlohmann::json_abi_v3_12_0::adl_serializer, std::__1::vector<unsigned char, std::__1::allocator<unsigned char>>, void> const&)> const&) chat.cpp:762 ggml-org#5 0x000100a2a7f4 in std::__1::__function::__func<common_chat_params_init_llama_3_x(minja::chat_template const&, templates_params const&, bool)::$_0, std::__1::allocator<common_chat_params_init_llama_3_x(minja::chat_template const&, templates_params const&, bool)::$_0>, void (common_grammar_builder const&)>::operator()(common_grammar_builder const&) function.h:319 ggml-org#6 0x000100aa98f4 in build_grammar(std::__1::function<void (common_grammar_builder const&)> const&, common_grammar_options const&) json-schema-to-grammar.cpp:982 ggml-org#7 0x0001009c9314 in common_chat_params_init_llama_3_x(minja::chat_template const&, templates_params const&, bool) chat.cpp:1110 ggml-org#8 0x0001009b8afc in common_chat_templates_apply_jinja(common_chat_templates const*, common_chat_templates_inputs const&) chat.cpp:1992 ggml-org#9 0x0001009b533c in common_chat_templates_apply(common_chat_templates const*, common_chat_templates_inputs const&) chat.cpp:2074 ggml-org#10 0x000100810120 in llamacpp_apply_chat_template+0x724 (predict_oai-98384e17fb94e863:arm64+0x100090120) ... ==45482==Register values: x[0] = 0x00006020004147f8 x[1] = 0x00006080000013c8 x[2] = 0x0000000000000000 x[3] = 0x0000604006289738 x[4] = 0x0000000000000002 x[5] = 0x0000000000000001 x[6] = 0x04034000004b4000 x[7] = 0x0000000000000001 x[8] = 0xbebebebebebebebe x[9] = 0x17d7d7d7d7d7d7d7 x[10] = 0x00000c04000828ff x[11] = 0x0000000000000001 x[12] = 0x000000002018d383 x[13] = 0x0000000000000000 x[14] = 0xfa0000000000fafa x[15] = 0x000010700001ffff x[16] = 0x000000019dc012c0 x[17] = 0x00000001021284f8 x[18] = 0x0000000000000000 x[19] = 0x00000001700acdc0 x[20] = 0x0000000000000002 x[21] = 0x000000002018d384 x[22] = 0x16dd16fd2e731151 x[23] = 0x0000007000020000 x[24] = 0x0000000100c69c08 x[25] = 0x0000000100c69c20 x[26] = 0x00006080000013c7 x[27] = 0x0000000100c69c00 x[28] = 0x00000001700acd60 fp = 0x00000001700aceb0 lr = 0x0000000100abce30 sp = 0x00000001700acd60 AddressSanitizer can not provide additional info. SUMMARY: AddressSanitizer: SEGV __hash_table:1565 in std::__1::pair<std::__1::__hash_iterator<std::__1::__hash_node<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, void*>*>, bool> std::__1::__hash_table<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, std::__1::hash<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>>, std::__1::equal_to<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>>, std::__1::allocator<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>>>::__emplace_unique_key_args<std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&>(std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&) Thread T5 created by T0 here: #0 0x0001020b99d4 in pthread_create+0x5c (libclang_rt.asan_osx_dynamic.dylib:arm64e+0x359d4) #1 0x000100873910 in std::sys::pal::unix::thread::Thread::new::h77254fdd87a28e05+0x118 (predict_oai-98384e17fb94e863:arm64+0x1000f3910) #2 0x0001007c7a1c in test::run_test::haeb3c2bcd5ed6cf6+0x76c (predict_oai-98384e17fb94e863:arm64+0x100047a1c) #3 0x0001007aedb0 in test::console::run_tests_console::he9d142d704f3a986+0x149c (predict_oai-98384e17fb94e863:arm64+0x10002edb0) #4 0x0001007c5758 in test::test_main::hf86a5e20735245b9+0x118 (predict_oai-98384e17fb94e863:arm64+0x100045758) ggml-org#5 0x0001007c5da0 in test::test_main_static::h61ee9c8fd30abca0+0x54 (predict_oai-98384e17fb94e863:arm64+0x100045da0) ... ==45482==ABORTING

ExtReMLapin and others added 30 commits August 11, 2025 18:21

Update chat.cpp to support (at least) qwen3 + tool_choice = required

c6c4f7c

refactored changes to follow string tern op

42937a5

fixing editorconfig-checker CI (tailing whitespace)

5796938

Merge branch 'ggml-org:master' into fix_qwen_reasoning_tool_calling_r…

de07a43

…equired

hermes 2 pro tool calling, better support for thinking (thinking tag …

79e4a7b

…already opened grammar)

qwen hermes tool calling : fixed grammar rules names

dbae921

fixed really weird grammar crash `Unexpected empty grammar stack afte…

86493dd

…r accepting piece:`

also apply the hotcrashfix here, just in case

bb5e352

reverted changes done to grammar_lazy for hermes 2

6d5f561

if there is enable_thinking enabled but hermes model doesn't support …

352274e

…it, just disable it, don't GGML_ABORT

fix thinking-content eating closing think tag | ref ggml-org#8953

0e55830

removed ? from grammar as it doesn't crash on linux, probably worth…

e62cd70

… it's own issue

server: higher timeout for tests (ggml-org#15621)

fbef0fa

kv-cache : remove LLAMA_SET_ROWS checks (ggml-org#15505)

8a4280c

ggml-ci

scripts: add sqlite3 check for compare-commits.sh (ggml-org#15633)

55042b3

kv-cache : fix find_slot to not search for continuous slot (ggml-org#…

c8d0d14

…15638) ggml-ci

ggml : fix SSM_SCAN for n_groups > 1 (ggml-org#15625)

7380414

ggml-cpu: fix invalid hsum build in debug s390x (ggml-org#15634)

6c442f4

Signed-off-by: Aaron Teo <[email protected]>

CUDA: add conv2d (ggml-org#15635)

c97dc09

* CUDA: add conv2d * CUDA: conv2d - correct formatting and added const

Merge branch 'ggml-org:master' into fix_qwen_reasoning_tool_calling_r…

2f28a1c

…equired

fixed crash with "auto" mode, trigger was missing

310701b

CUDA: fuse adds, fuse add with rms norm (ggml-org#15631)

009b709

* CUDA: fused add with rms_norm_mul * Non-broadcast fuse works * Add fused adds * format * Remove n_fuse from template params * Address review comments * Move template inside binbcast

chaxu01 and others added 16 commits August 31, 2025 00:03

ggml: update kleidiai to v1.13.0 (ggml-org#15663)

4d74393

vulkan: clamp matmul and FA results to the max finite value (ggml-org…

94e82c7

…#15652) * vulkan: clamp matmul and FA results to the max finite value * only clamp for fp16

vulkan: Allow fallback to sysmem memory when vidmem is full (ggml-org…

b97c9ed

…#15649) * vulkan: Allow fallback to sysmem memory when vidmem is full * vulkan: Add env var GGML_VK_ALLOW_SYSMEM_FALLBACK

vulkan: handle large sizes for get_rows (ggml-org#15686)

bbbf5ec

ci : explicitly set fa off or on (ggml-org#15692)

7d3c9f2

llama : separate compute buffer reserve from fattn check (ggml-org#15696

9777032

) Exposes ggml_backend_sched_split_graph() to allow splitting the graph without allocating compute buffers and uses it to split the graph for the automatic Flash Attention check.

llama : fix fattn reserve call n_seqs parameter (ggml-org#15699)

2749662

ggml-ci

metal : fix checks for available FA kernels (ggml-org#15700)

4efd5a8

* metal : fix checks for available FA kernels ggml-ci * cont : fix comment [no ci]

server : enable /slots by default and make it secure (ggml-org#15630)

0d161f0

* server : enable /slots by default and make it secure ggml-ci * server : fix tests to pass `--no-slots` when necessary * server : extend /props with info about enabled endpoints

CANN: Optimize MUL_MAT_ID (ggml-org#15658)

b9382c3

Merge branch 'ggml-org:master' into fix_qwen_reasoning_tool_calling_r…

5688afa

…equired

ExtReMLapin merged commit 7a8e3c4 into master2 Sep 1, 2025
49 of 54 checks passed

github-actions bot added documentation Improvements or additions to documentation Apple Metal Nvidia GPU Vulkan testing examples devops python script server ggml Ascend NPU labels Sep 1, 2025

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Uh oh!

Fix qwen reasoning tool calling required #3

Fix qwen reasoning tool calling required #3

Uh oh!

ExtReMLapin commented Sep 1, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

21 participants

Uh oh!

Fix qwen reasoning tool calling required #3

Fix qwen reasoning tool calling required #3

Uh oh!

Conversation

ExtReMLapin commented Sep 1, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

21 participants