]>
git.djapps.eu Git - pkg/ggml/sources/llama.cpp/log
Johannes Gäßler [Wed, 14 May 2025 14:41:02 +0000 (16:41 +0200)]
CUDA: fix crash on large batch size for quant. MoE (#13537)
Diego Devesa [Wed, 14 May 2025 14:12:36 +0000 (07:12 -0700)]
llama : fix quantize with dl backends (#13539)
Johannes Gäßler [Wed, 14 May 2025 14:08:20 +0000 (16:08 +0200)]
CUDA: faster Deepseek FA, add Turing support (#13435)
Gabe Goodhart [Wed, 14 May 2025 12:53:59 +0000 (06:53 -0600)]
fix: Move build_inp_pos to the top of the graph section for build_granite (#13538)
This matches how others do it, but will still avoid the extra
initialization when rope is disabled.
Branch: GraniteFour
Signed-off-by: Gabe Goodhart <redacted>
Georgi Gerganov [Wed, 14 May 2025 12:42:10 +0000 (15:42 +0300)]
server : passthrough the /models endpoint during loading (#13535)
* server : passthrough the /models endpoint during loading
* server : update readme + return json for "meta" field
Xuan-Son Nguyen [Wed, 14 May 2025 11:35:07 +0000 (13:35 +0200)]
server : fix cache_tokens bug with no cache_prompt (#13533)
bandoti [Wed, 14 May 2025 10:53:57 +0000 (07:53 -0300)]
cmake: simplify vulkan shader test logic (#13263)
Jeff Bolz [Wed, 14 May 2025 09:55:26 +0000 (18:55 +0900)]
vulkan: KHR_coopmat flash attention (#13506)
This shader uses coopmat1 to do the Q*K^T multiply. The P*V multiply is more
difficult for various reasons so I haven't done it. Performance for this
shader is around 2.5x better than for the scalar shader when doing prompt
processing. Some of the benefit may be from other optimizations like staging
through shared memory, or splitting by rows.
Xuan-Son Nguyen [Wed, 14 May 2025 08:26:12 +0000 (10:26 +0200)]
webui : use fflate for more deterministic gzip compress (#13525)
* webui : use pako for more deterministic gzip compress
* simpler code
* use fflate instead of pako
Luca Stefani [Wed, 14 May 2025 08:07:31 +0000 (10:07 +0200)]
webui: Allow pasting file from clipboard (#13526)
* server: Allow pasting file from clipboard
* server: Prevent default action on file paste
* update build
* format then build combined
---------
Co-authored-by: Xuan Son Nguyen <redacted>
ddpasa [Wed, 14 May 2025 07:59:12 +0000 (09:59 +0200)]
docs: Update link to ggml-org in multimodal.md (#13513)
* Update multimodal.md
Minor change to include the huggingface link
* Update docs/multimodal.md
---------
Co-authored-by: Xuan-Son Nguyen <redacted>
Sigbjørn Skjæret [Wed, 14 May 2025 06:41:01 +0000 (08:41 +0200)]
scripts : fix compare-llama-bench.py show parameter (#13514)
Jeff Bolz [Wed, 14 May 2025 04:15:50 +0000 (13:15 +0900)]
vulkan: workaround FA compile failures on macos (#13517)
Ed Addario [Tue, 13 May 2025 17:12:31 +0000 (18:12 +0100)]
quantize : improve tensor-type pattern matching (#13033)
Xuan-Son Nguyen [Tue, 13 May 2025 15:07:21 +0000 (17:07 +0200)]
clip : clip.h become private API (⚠️ breaking change) (#13510)
Georgi Gerganov [Tue, 13 May 2025 15:04:39 +0000 (18:04 +0300)]
metal : use FA-vec kernel up to batch size 20 (#13496)
* batched-bench : fix pp batch contents
* metal : optimize multi-sequence FA vec kernel
ggml-ci
* metal : use FA-vec kernel up to batch size 20
ggml-ci
Georgi Gerganov [Tue, 13 May 2025 15:04:00 +0000 (18:04 +0300)]
metal : optimize multi-sequence FA vec kernel (#13493)
* batched-bench : fix pp batch contents
* metal : optimize multi-sequence FA vec kernel
ggml-ci
Dan Johansson [Tue, 13 May 2025 15:02:28 +0000 (17:02 +0200)]
ggml-cpu: Update KleidiAI to v1.6 and fix include directives (#13509)
Signed-off-by: Dan Johansson <redacted>
Georgi Gerganov [Tue, 13 May 2025 15:01:53 +0000 (18:01 +0300)]
batched-bench : fix pp batch contents (#13492)
Xuan-Son Nguyen [Tue, 13 May 2025 13:33:58 +0000 (15:33 +0200)]
mtmd : remove libllava, remove clip-quantize-cli (⚠️ breaking change) (#13460)
* mtmd : remove libllava, remove clip-quantize-cli
* rm clip_model_quantize
Sigbjørn Skjæret [Tue, 13 May 2025 13:31:12 +0000 (15:31 +0200)]
scripts : support arbitrary input file formats in compare-llama-bench.py (#13455)
Gabe Goodhart [Tue, 13 May 2025 13:12:01 +0000 (07:12 -0600)]
model : Granite MoE shared (#13269)
* feat: Add GGUF conversion for granitemoeshared
Branch: GraniteMoEShared
Signed-off-by: Gabe Goodhart <redacted>
* feat: hparam and arch plumbing for granitemoeshared
Branch: GraniteMoEShared
Signed-off-by: Gabe Goodhart <redacted>
* fix: Split MoE fused tensors for shared experts in conversion
Branch: GraniteMoEShared
Signed-off-by: Gabe Goodhart <redacted>
* feat: First WIP cut at model arch in cpp
The hparam and architecture plumbing should be correct, but the
implementation of the shared experts seems to still be broken.
Branch: GraniteMoEShared
Signed-off-by: Gabe Goodhart <redacted>
* fix: Cleaner (maybe more correct?) splitting for gate/up
Branch: GraniteMoEShared
Signed-off-by: Gabe Goodhart <redacted>
* fix: Fix the input to the shared experts
I had misread that the shared experts take the inputs _before_ the standard
MoE layer and was feeding the output of the MoE to the shared experts.
Branch: GraniteMoEShared
Signed-off-by: Gabe Goodhart <redacted>
* fix: Avoid architecture-specific checks for Granite MoE Shared
This is a cleaner way that will allow more flexibility in architecture
strings going forward.
Branch: GraniteMoEShared
Signed-off-by: Gabe Goodhart <redacted>
* refactor: Split granite architectures out of llm_build_llama
This helps de-clutter the llama-family graph construction and allows
granite to diverge further (in preparation for Granite 4).
NOTE: I removed the granite scale factors from llm_build_deci because they
appear to only be there as copy-paste from llm_build_llama. The HF config
does not seem to set those values:
https://huggingface.co/Deci/DeciLM-7B/blob/main/config.json
Branch: GraniteMoEShared
Signed-off-by: Gabe Goodhart <redacted>
* fix: Fix compiler warning about uninitialized inp_pos
This should not have been reachable, but it warns on some compliers
Branch: GraniteMoEShared
Signed-off-by: Gabe Goodhart <redacted>
* fix: Consoladate GraniteMoEShared into GraniteMoE for conversion
Branch: GraniteMoEShared
Signed-off-by: Gabe Goodhart <redacted>
* fix: Consolidate GraniteMoEShared into GraniteMoE on the c++ side
Branch: GraniteMoEShared
Signed-off-by: Gabe Goodhart <redacted>
---------
Signed-off-by: Gabe Goodhart <redacted>
Georgi Gerganov [Tue, 13 May 2025 11:01:45 +0000 (14:01 +0300)]
sync : ggml
Diego Devesa [Mon, 12 May 2025 22:31:37 +0000 (15:31 -0700)]
llama-bench : add defrag-thold, check for invalid ranges (#13487)
lhez [Mon, 12 May 2025 20:13:49 +0000 (13:13 -0700)]
opencl: remove unnecessary assert for `add` (#13257)
Xuan-Son Nguyen [Mon, 12 May 2025 13:06:51 +0000 (15:06 +0200)]
clip : cap max image size 1024 for qwen vl model (#13478)
Johannes Gäßler [Mon, 12 May 2025 12:44:49 +0000 (14:44 +0200)]
llama/ggml: add LLM training support (#10544)
* llama/ggml: add LLM training support
more compact progress bar
llama_save_model_to_file
llama_opt_param_filter
ggml_graph_dup force_grads
refactor ggml_opt, fix test-opt
* remove logits_all
* refactor CUDA implementation for ACC
* reset graph at beginning of opt period
Georgi Gerganov [Mon, 12 May 2025 12:12:27 +0000 (15:12 +0300)]
context : fix state io for memory-less contexts (#13470)
ggml-ci
Anudit Nagar [Mon, 12 May 2025 11:56:42 +0000 (18:56 +0700)]
server : allow content to be null in oaicompat_completion_params_parse (#13477)
Diego Devesa [Mon, 12 May 2025 11:08:22 +0000 (13:08 +0200)]
llama-bench : accept ranges for integer parameters (#13410)
Dan Johansson [Mon, 12 May 2025 11:06:19 +0000 (13:06 +0200)]
ggml-cpu: Integrate fp32=bf16xbf16 SME KleidiAI kernel (#13053)
* ggml-cpu: Integrate fp32=bf16xbf16 SME KleidiAI kernel
Signed-off-by: Dan Johansson <redacted>
* * code review fixes
Signed-off-by: Dan Johansson <redacted>
* * adds a comment that clarifies barrier usage
Signed-off-by: Dan Johansson <redacted>
---------
Signed-off-by: Dan Johansson <redacted>
Co-authored-by: Charles Xu <redacted>
Johannes Gäßler [Mon, 12 May 2025 08:51:21 +0000 (10:51 +0200)]
CUDA: fix misaligned synchronization in FA (#13469)
Xuan-Son Nguyen [Mon, 12 May 2025 08:29:13 +0000 (10:29 +0200)]
ggml : add mrope kernel for metal (#13457)
Atharva Dubey [Mon, 12 May 2025 05:15:32 +0000 (06:15 +0100)]
enable dpcpp nightly builds with libraries (#13406)
City [Sun, 11 May 2025 22:39:06 +0000 (00:39 +0200)]
mtmd : Use RMS norm for InternVL 3 38B and 78B mmproj (#13459)
Anthony Umfer [Sun, 11 May 2025 15:08:26 +0000 (11:08 -0400)]
tools : fix uninitialized llama_batch in server (#13436)
* add constructor to initialize server_context::batch, preventing destructor's call to llama_batch_free from causing an invalid free()
* Update tools/server/server.cpp
Co-authored-by: Xuan-Son Nguyen <redacted>
* use C++11 initializer syntax
* switch from Copy-list-initialization to Direct-list-initialization
---------
Co-authored-by: Xuan-Son Nguyen <redacted>
Sigbjørn Skjæret [Sun, 11 May 2025 14:20:39 +0000 (16:20 +0200)]
scripts : exit compare-llama-bench.py gracefully when there's nothing to compare (#13451)
Johannes Gäßler [Sun, 11 May 2025 14:09:33 +0000 (16:09 +0200)]
CUDA: fix crash with partial offloading of MoE (#13439)
David Huang [Sun, 11 May 2025 12:18:39 +0000 (20:18 +0800)]
Add `--no-op-offload` to improve `-ot` pp perf in MoE models like llama4 400B (#13386)
City [Sun, 11 May 2025 09:35:52 +0000 (11:35 +0200)]
mtmd : support InternVL 3 38B and 78B mmproj (#13443)
* Support InternVL 3 38B and 78B mmproj
* Swap norms in clip.cpp
* Group variables together
Xuan-Son Nguyen [Sun, 11 May 2025 09:34:23 +0000 (11:34 +0200)]
mtmd : move helpers to dedicated file (#13442)
* mtmd : move helpers to dedicated file
* fix windows build
* rm redundant include
Thomas Germer [Sat, 10 May 2025 20:26:46 +0000 (22:26 +0200)]
docs : Fix typo in InternVL3 model name (#13440)
Johannes Gäßler [Sat, 10 May 2025 20:22:48 +0000 (22:22 +0200)]
CUDA: fix race conditions FlashAttention kernels (#13438)
Sigbjørn Skjæret [Sat, 10 May 2025 20:08:07 +0000 (22:08 +0200)]
vocab : add ByteDance-Seed/Seed-Coder (#13423)
Xuan-Son Nguyen [Sat, 10 May 2025 17:57:54 +0000 (19:57 +0200)]
mtmd : add hard limit on image resolution for qwen2vl / qwen2.5vl (#13434)
* mtmd : add hard limit on image resolution for qwen2vl / qwen2.5vl
* fix typo
Xuan-Son Nguyen [Sat, 10 May 2025 16:44:49 +0000 (18:44 +0200)]
server : update docs (#13432)
Sigbjørn Skjæret [Sat, 10 May 2025 15:19:52 +0000 (17:19 +0200)]
llguidance : set tokenizer slices to default (#13424)
Thammachart Chinvarapon [Sat, 10 May 2025 14:34:48 +0000 (21:34 +0700)]
ci: free_disk_space flag enabled for intel variant (#13426)
before cleanup: 20G
after cleanup: 44G
after all built and pushed: 24G
https://github.com/Thammachart/llama.cpp/actions/runs/
14945093573 /job/
41987371245
Xuan-Son Nguyen [Sat, 10 May 2025 14:26:42 +0000 (16:26 +0200)]
mtmd : support InternVL 2.5 and 3 (#13422)
* convert : internvl support
* InternVL3-1B working
* fix regression
* rm mobilevlm from test
* fix conversion
* add test for internvl
* add to list of pre-quant
* restore boi/eoi check
* add clarify comment for norm eps
Johannes Gäßler [Sat, 10 May 2025 07:16:52 +0000 (09:16 +0200)]
CUDA: fix FlashAttention on Turing (#13415)
Xuan-Son Nguyen [Sat, 10 May 2025 06:16:29 +0000 (08:16 +0200)]
arg : add env var to control mmproj (#13416)
* arg : add env var to control mmproj
* small note about -hf --mmproj
Jeff Bolz [Sat, 10 May 2025 06:07:07 +0000 (23:07 -0700)]
vulkan: scalar flash attention implementation (#13324)
* vulkan: scalar flash attention implementation
* vulkan: always use fp32 for scalar flash attention
* vulkan: use vector loads in scalar flash attention shader
* vulkan: remove PV matrix, helps with register usage
* vulkan: reduce register usage in scalar FA, but perf may be slightly worse
* vulkan: load each Q value once. optimize O reduction. more tuning
* vulkan: support q4_0/q8_0 KV in scalar FA
* CI: increase timeout to accommodate newly-supported tests
* vulkan: for scalar FA, select between 1 and 8 rows
* vulkan: avoid using Float16 capability in scalar FA
Helton Reis [Fri, 9 May 2025 20:15:39 +0000 (17:15 -0300)]
chore(llguidance): use tagged version that does not break the build (#13413)
Xuan-Son Nguyen [Fri, 9 May 2025 17:29:37 +0000 (19:29 +0200)]
server : vision support via libmtmd (#12898)
* server : (experimental) vision support via libmtmd
* mtmd : add more api around mtmd_image_tokens
* mtmd : add more api around mtmd_image_tokens
* mtmd : ability to calc image hash
* shared_ptr for mtmd_image_tokens
* move hash to user-define ID (fixed)
* abstract out the batch management
* small fix
* refactor logic adding tokens to batch
* implement hashing image
* use FNV hash, now hash bitmap instead of file data
* allow decoding image embedding to be split into batches
* rm whitespace
* disable some features when mtmd is on
* fix --no-mmproj-offload
* mtmd_context_params no timings
* refactor server_inp to server_tokens
* fix the failing test case
* init
* wip
* working version
* add mtmd::bitmaps
* add test target
* rm redundant define
* test: mtmd_input_chunks_free
* rm outdated comment
* fix merging issue
* explicitly create mtmd::input_chunks
* mtmd_input_chunk_copy
* add clone()
* improve server_input struct
* clip : fix confused naming ffn_up and ffn_down
* rm ffn_i/o/g naming
* rename n_embd, n_ff
* small fix
* no check n_ff
* fix detokenize
* add const to various places
* add warning about breaking changes
* add c api
* helper: use mtmd_image_tokens_get_n_pos
* fix ctx_shift
* fix name shadowing
* more strict condition
* support remote image_url
* remote image_url log
* add CI test
* do not log base64
* add "has_multimodal" to /props
* remove dangling image
* speculative: use slot.cache_tokens.insert
* Apply suggestions from code review
Co-authored-by: Georgi Gerganov <redacted>
* rm can_be_detokenized
* on prmpt processing done, assert cache_tokens.size
* handle_completions_impl returns void
* adapt the new web ui
* update docs and hot topics
* rm assert
* small fix (2)
---------
Co-authored-by: Georgi Gerganov <redacted>
Alberto Cabrera Pérez [Fri, 9 May 2025 15:34:08 +0000 (16:34 +0100)]
sycl : implementation of reordered Q4_0 MMVQ for Intel GPUs (#12858)
* sycl : Implemented reorder Q4_0 mmvq
Signed-off-by: Alberto Cabrera <redacted>
* sycl : Fixed mmvq being called when reorder is disabled
* sycl : Improved comments in the quants header
Signed-off-by: Alberto Cabrera <redacted>
* Use static_assert
* safe_div -> ceil_div
* Clarify qi comment
* change the reorder tensor from init to execute OP
* dbg
* Undo changes to test-backend-ops
* Refactor changes on top of q4_0 reorder fix
* Missing Reverts
* Refactored opt_for_reorder logic to simplify code path
* Explicit inlining and unroll
* Renamed mul_mat_algo enum for consistency
---------
Signed-off-by: Alberto Cabrera <redacted>
Co-authored-by: romain.biessy <redacted>
Georgi Gerganov [Fri, 9 May 2025 12:14:56 +0000 (15:14 +0300)]
metal : optimize MoE for large batches (#13388)
ggml-ci
Johannes Gäßler [Fri, 9 May 2025 11:34:58 +0000 (13:34 +0200)]
CUDA: FA support for Deepseek (Ampere or newer) (#13306)
* CUDA: FA support for Deepseek (Ampere or newer)
* do loop unrolling via C++ template
Diego Devesa [Fri, 9 May 2025 11:02:07 +0000 (13:02 +0200)]
llama : do not crash if there is no CPU backend (#13395)
* llama : do not crash if there is no CPU backend
* add checks to examples
Johannes Gäßler [Fri, 9 May 2025 10:14:04 +0000 (12:14 +0200)]
CUDA: fix crash on large batch size for MoE models (#13384)
Bartowski [Fri, 9 May 2025 09:53:58 +0000 (05:53 -0400)]
imatrix : Add --parse-special for enabling parsing of special tokens in imatrix calculation (#13389)
* Add --parse-special for enabling parsing of special tokens in imatrix calculation
* whitespace
R0CKSTAR [Fri, 9 May 2025 09:25:50 +0000 (17:25 +0800)]
llama-run: add support for downloading models from ModelScope (#13370)
Signed-off-by: Xiaodong Ye <redacted>
Xuan-Son Nguyen [Fri, 9 May 2025 09:18:02 +0000 (11:18 +0200)]
mtmd : fix batch_view for m-rope (#13397)
* mtmd : fix batch_view for m-rope
* nits : fix comment
Xuan-Son Nguyen [Fri, 9 May 2025 09:17:51 +0000 (11:17 +0200)]
llama : one-off chat template fix for Mistral-Small-2503 (#13398)
* llama : one-off chat template fix for Mistral-Small-2503
* update readme
* add mistral-v7-tekken
Radoslav Gerganov [Fri, 9 May 2025 07:31:07 +0000 (10:31 +0300)]
rpc : add rpc_msg_set_tensor_hash_req (#13353)
* rpc : add rpc_msg_set_tensor_hash_req
Use a dedicated struct for the request of RPC_CMD_SET_TENSOR_HASH which
makes the code cleaner.
* fix
Jeff Bolz [Fri, 9 May 2025 07:23:41 +0000 (02:23 -0500)]
vulkan: Allow up to 4096 elements for mul_mat_id row_ids (#13326)
This assert fired running Qwen_Qwen3-30B-A3B-Q2_K.gguf:
GGML_ASSERT(nei0 * nei1 <= 3072);
The tensor is 8 x 512. Increase this array size to accommodate.
Xuan-Son Nguyen [Fri, 9 May 2025 07:06:37 +0000 (09:06 +0200)]
server : (webui) rename has_multimodal --> modalities (#13393)
* server : (webui) rename has_multimodal --> modalities
* allow converting SVG to PNG
* less complicated code
Diego Devesa [Thu, 8 May 2025 21:45:22 +0000 (23:45 +0200)]
ci : limit write permission to only the release step + fixes (#13392)
* ci : limit write permission to only the release step
* fix win cuda file name
* fix license file copy on multi-config generators
Matt Clayton [Thu, 8 May 2025 18:25:39 +0000 (14:25 -0400)]
mtmd : Expose helper_decode_image_chunk (#13366)
* mtmd: Expose helper_decode_image, output_embd_copy, image_tokens_copy/free
* Slim down
* Cleanups
Xuan-Son Nguyen [Thu, 8 May 2025 16:51:45 +0000 (18:51 +0200)]
server : (webui) fix a very small misalignment (#13387)
* server : (webui) fix a very small misalignment
* restore font-bold
Xuan-Son Nguyen [Thu, 8 May 2025 13:37:29 +0000 (15:37 +0200)]
server : (webui) revamp the input area, plus many small UI improvements (#13365)
* rework the input area
* process selected file
* change all icons to heroicons
* fix thought process collapse
* move conversation more menu to sidebar
* sun icon --> moon icon
* rm default system message
* stricter upload file check, only allow image if server has mtmd
* build it
* add renaming
* better autoscroll
* build
* add conversation group
* fix scroll
* extra context first, then user input in the end
* fix <hr> tag
* clean up a bit
* build
* add mb-3 for <pre>
* throttle adjustTextareaHeight to make it less laggy
* (nits) missing padding in sidebar
* rm stray console log
Sigbjørn Skjæret [Thu, 8 May 2025 13:34:29 +0000 (15:34 +0200)]
convert : support rope_scaling type and rope_type (#13349)
welix [Thu, 8 May 2025 13:03:53 +0000 (22:03 +0900)]
mtmd : fix the calculation of n_tokens for smolvlm (#13381)
Co-authored-by: Taichi Nishimura <redacted>
Georgi Gerganov [Thu, 8 May 2025 11:28:33 +0000 (14:28 +0300)]
context : allow cache-less context for embeddings (#13108)
* context : allow cache-less context for embeddings
ggml-ci
* context : enable reranking with encode()
ggml-ci
* context : encode() clears embd_seq
ggml-ci
* examples : use llama_encode() when appropriate
ggml-ci
* models : nomic bert moe does not require KV cache
* llama : update comments for llama_decode/llama_encode
ggml-ci
* context : update warning log [no ci]
Georgi Gerganov [Thu, 8 May 2025 11:26:50 +0000 (14:26 +0300)]
context : remove logits_all flag (#13284)
* context : remove logits_all flag
ggml-ci
* llama : remove logits_all flag + reorder llama_context_params
ggml-ci
Diego Devesa [Thu, 8 May 2025 11:15:28 +0000 (13:15 +0200)]
ci : move release workflow to a separate file (#13362)
Diego Devesa [Thu, 8 May 2025 11:15:15 +0000 (13:15 +0200)]
llama : print size and type of overridden tensors (#13364)
Alberto Cabrera Pérez [Thu, 8 May 2025 09:08:01 +0000 (10:08 +0100)]
sycl: addressing non-contiguous src1 mul_mats (nc and batched) (#13343)
* sycl: fixed non-contiguous src1 mul_mats (nc and batched)
* Fixed wrong static_cast inside kernel
Diego Devesa [Wed, 7 May 2025 14:36:33 +0000 (16:36 +0200)]
docker : disable arm64 and intel images (#13356)
Georgi Gerganov [Wed, 7 May 2025 13:39:36 +0000 (16:39 +0300)]
sync : ggml
ggml-ci
Daniel Bevenius [Mon, 5 May 2025 11:09:35 +0000 (13:09 +0200)]
whisper: remove MSVC warnings pragmas (whisper/3090)
* ggml : remove MSVC warnings pragmas
This commit removes the MSVC-specific pragmas as these are now handled
in ggml/CMakeLists.txt.
* whisper : remove MSVC warning pragmas
This commit removes the MSVC-specific pragmas. These are now handled in
the ggml/CMakeLists.txt file.
Jared Tweed [Fri, 2 May 2025 09:41:35 +0000 (02:41 -0700)]
cmake : removed stdc++fs (whisper/3097)
* removed stdc++fs
* kept line, but removed stdc++fs
Sigbjørn Skjæret [Wed, 7 May 2025 10:49:27 +0000 (12:49 +0200)]
llama : deci : support ffn-free with attention (#13296)
Ycros [Wed, 7 May 2025 08:23:28 +0000 (18:23 +1000)]
common : Add a warning when we can't match samplers from a string or char. (#13330)
R0CKSTAR [Wed, 7 May 2025 07:48:23 +0000 (15:48 +0800)]
cuda : remove nrows_x in mul_mat_q_process_tile (#13325)
Signed-off-by: Xiaodong Ye <redacted>
Georgi Gerganov [Wed, 7 May 2025 07:28:02 +0000 (10:28 +0300)]
examples : remove infill (#13283)
ggml-ci
piDack [Wed, 7 May 2025 07:23:11 +0000 (15:23 +0800)]
llama : support tie embedding for chatglm models (#13328)
Johannes Gäßler [Tue, 6 May 2025 21:35:51 +0000 (23:35 +0200)]
CUDA: mix virt/real CUDA archs for GGML_NATIVE=OFF (#13135)
Xuan-Son Nguyen [Tue, 6 May 2025 20:40:24 +0000 (22:40 +0200)]
clip : refactor graph builder (#13321)
* mtmd : refactor graph builder
* fix qwen2vl
* clean up siglip cgraph
* pixtral migrated
* move minicpmv to a dedicated build function
* move max_feature_layer to build_llava
* use build_attn for minicpm resampler
* fix windows build
* add comment for batch_size
* also support tinygemma3 test model
* qwen2vl does not use RMS norm
* fix qwen2vl norm (2)
DocShotgun [Tue, 6 May 2025 20:36:24 +0000 (13:36 -0700)]
sampling : make top_n_sigma no-op at <=0 or a single candidate (#13345)
oobabooga [Tue, 6 May 2025 18:24:15 +0000 (15:24 -0300)]
sampling : don't consider -infinity values in top_n_sigma (#13344)
Diego Devesa [Tue, 6 May 2025 18:15:31 +0000 (20:15 +0200)]
cmake : remove arm64 msvc presets (#13342)
Akarshan Biswas [Tue, 6 May 2025 14:57:06 +0000 (20:27 +0530)]
SYCL: Disable reorder optimize by default and stop setting tensor extras when optimize is disabled (#13254)
* SYCL: Do not set tensor extras when reorder optimize is disabled
* SYCL: Disable reorder optimize by default
Xuan-Son Nguyen [Tue, 6 May 2025 12:25:40 +0000 (14:25 +0200)]
llama : fix build_ffn without gate (#13336)
* llama : fix build_ffn without gate
* fix build on windows
* Revert "fix build on windows"
This reverts commit
fc420d3c7eef3481d3d2f313fef2757cb33a7c56 .
Johannes Gäßler [Tue, 6 May 2025 11:58:51 +0000 (13:58 +0200)]
CUDA: fix bad asserts for partial offload (#13337)
Sigbjørn Skjæret [Tue, 6 May 2025 09:12:06 +0000 (11:12 +0200)]
convert : qwen2/3moe : set yarn metadata if present (#13331)
* set yarn metadata if present
* add comment about enabling YaRN
Co-authored-by: Xuan-Son Nguyen <redacted>
---------
Co-authored-by: Xuan-Son Nguyen <redacted>
Johannes Gäßler [Tue, 6 May 2025 06:36:46 +0000 (08:36 +0200)]
CUDA: fix --split-mode row for MMQ (#13323)
compilade [Tue, 6 May 2025 02:27:31 +0000 (22:27 -0400)]
gguf-py : avoid requiring pyside6 for other scripts (#13036)
- gguf-py : remove gguf-py/gguf/scripts/__init__.py because it's not needed
Implicit namespaces are supported since Python 3.3 (https://peps.python.org/pep-0420/),
and the entrypoints in pyproject.toml can directly refer to the main functions.
Johannes Gäßler [Mon, 5 May 2025 20:32:13 +0000 (22:32 +0200)]
CUDA: fix logic for clearing padding with -ngl 0 (#13320)
oobabooga [Mon, 5 May 2025 20:12:19 +0000 (17:12 -0300)]
sampling : Integrate Top-nσ into main sampling chain (and add it to the server) (#13264)
* sampling: add Top-nσ sampler to `llama-server` and sampler ordering
* revert: sampler ordering
* revert: VS' crappy auto-formatting
* revert: VS' crappy auto-formatting pt.2
* revert: my crappy eye sight...
* sampling: add XTC to Top-nσ sampler chain
* sampling: add Dyna. Temp. to Top-nσ sampler chain
* sampling: actually remove Top-nσ from sampler(oops)
* Integrate top_n_sigma into main sampler chain
* Define COMMON_SAMPLER_TYPE_TOP_N_SIGMA
* Formatting
* Lint
* Exit early in the sampler if nsigma < 0
---------
Co-authored-by: CasualAutopsy <redacted>
igardev [Mon, 5 May 2025 14:03:31 +0000 (17:03 +0300)]
server : Webui - change setText command from parent window to also send the message. (#13309)
* setText command from parent window for llama-vscode now sends the message automatically.
* Upgrade packages versions to fix vulnerabilities with "npm audit fix" command.
* Fix code formatting.
* Add index.html.gz changes.
* Revert "Upgrade packages versions to fix vulnerabilities with "npm audit fix" command."
This reverts commit
67687b7fda8a293724ba92ea30bb151677406bc8 .
* easier approach
* add setTimeout
---------
Co-authored-by: igardev <redacted>
Co-authored-by: Xuan Son Nguyen <redacted>