]>
git.djapps.eu Git - pkg/ggml/sources/llama.cpp/log
Georgi Gerganov [Tue, 24 Dec 2024 07:44:20 +0000 (09:44 +0200)]
llama : the WPM vocabs use the CLS token as BOS (#10930)
* llama : the WPM vocabs use the CLS token as BOS
ggml-ci
* llama : add comment
Diego Devesa [Tue, 24 Dec 2024 03:05:27 +0000 (04:05 +0100)]
ggml : use wstring for backend search paths (#10960)
ggml-ci
Diego Devesa [Tue, 24 Dec 2024 03:05:17 +0000 (04:05 +0100)]
ggml : fix arm enabled features check (#10961)
Diego Devesa [Mon, 23 Dec 2024 19:25:52 +0000 (20:25 +0100)]
ggml : fix const usage in SSE path (#10962)
Xuan Son Nguyen [Mon, 23 Dec 2024 11:52:25 +0000 (12:52 +0100)]
server : fix missing model id in /model endpoint (#10957)
* server : fix missing model id in /model endpoint
* fix ci
Xuan Son Nguyen [Mon, 23 Dec 2024 11:02:44 +0000 (12:02 +0100)]
server : add system_fingerprint to chat/completion (#10917)
* server : add system_fingerprint to chat/completion
* update README
Radoslav Gerganov [Mon, 23 Dec 2024 08:39:30 +0000 (10:39 +0200)]
rpc-server : add support for the SYCL backend (#10934)
Yun Dou [Mon, 23 Dec 2024 00:35:44 +0000 (08:35 +0800)]
llama : support InfiniAI Megrez 3b (#10893)
* Support InfiniAI Megrez 3b
* Fix tokenizer_clean_spaces for megrez
ymcki [Mon, 23 Dec 2024 00:22:33 +0000 (08:22 +0800)]
llama : support for Llama-3_1-Nemotron-51B (#10669)
* conflict resolution
* move comments after bracket to its own line
Eric Curtin [Mon, 23 Dec 2024 00:21:40 +0000 (00:21 +0000)]
llama-run : include temperature option (#10899)
This commit updates the `examples/run/README.md` file to include a new
option for setting the temperature and updates the `run.cpp` file to
parse this option.
Signed-off-by: Eric Curtin <redacted>
yuri@FreeBSD [Mon, 23 Dec 2024 00:20:11 +0000 (16:20 -0800)]
ggml : fix run-time on FreeBSD in get_executable_path() (#10948)
Rudi Servo [Sun, 22 Dec 2024 22:22:58 +0000 (21:22 -0100)]
devops : add docker-multi-stage builds (#10832)
Billel Mokeddem [Sun, 22 Dec 2024 22:09:58 +0000 (01:09 +0300)]
llama : add Falcon3 support (#10883)
* Add Falcon3 model support
* Add fix for adding bos to added special tokens
* Add comment explaining the logic behind the if statement
* Add a log message to better track the when the following line of code is triggered
* Update log to only print when input and output characters are different
* Fix handling pre-normalized tokens
* Refactoring
Jeff Bolz [Sun, 22 Dec 2024 09:44:01 +0000 (03:44 -0600)]
vulkan: build fixes for 32b (#10927)
* vulkan: build fixes for 32b
Should fix #10923
* vulkan: initialize some buffer/offset variables
Georgi Gerganov [Sat, 21 Dec 2024 08:10:18 +0000 (10:10 +0200)]
convert : add BertForMaskedLM (#10919)
Jeff Bolz [Sat, 21 Dec 2024 07:04:45 +0000 (01:04 -0600)]
vulkan: optimize coopmat2 dequant functions (#10855)
Change the code to do 16b loads when possible and extract the appropriate
component late, so the code is effectively decoding a pair of elements and
then selecting one. This can allow more commoning to happen in the compiler
when neighboring elements are loaded.
Adrien Gallouët [Fri, 20 Dec 2024 23:33:37 +0000 (00:33 +0100)]
ggml-cpu: replace NEON asm with intrinsics in ggml_gemv_q4_0_4x8_q8_0() (#10874)
* ggml-cpu: replace NEON asm with intrinsics in ggml_gemv_q4_0_4x8_q8_0()
Signed-off-by: Adrien Gallouët <redacted>
* ggml-cpu: format code
Signed-off-by: Adrien Gallouët <redacted>
---------
Signed-off-by: Adrien Gallouët <redacted>
Akarshan Biswas [Fri, 20 Dec 2024 15:31:28 +0000 (21:01 +0530)]
SYCL: Migrate away from deprecated ggml_tensor->backend (#10840)
* Migrate to tensor->buffer for checking backend buffer type: 1
* SYCL: common.cpp try to migrate away from tensor->backend
* SYCL: fix assertions and add proper comments
* SYCL: remove extra space
* SYCL: Add back static to ggml_backend_buffer_is_sycl_split function
* SYCL: Add pragma directive to suppress warning spam
* SYCL: Integrate debug logs with GGML_LOG and other fixes
* Revert "SYCL: Integrate debug logs with GGML_LOG and other fixes"
This reverts commit
2607b7de0f0d2f4f1f690226f86fa861aa39cb97 .
Let's keep the current SYCL specific logging mechanism for now
* SYCL: Use GGML_SYCL_DEBUG after reverting
* SYCL: reg_get_proc_address func, update to the current func signature
* SYCL: Refactor SYCL buffer checks in ggml_sycl_cpy_tensor_2d
Xuan Son Nguyen [Fri, 20 Dec 2024 13:12:06 +0000 (14:12 +0100)]
server : (UI) fix copy to clipboard function (#10916)
Diego Devesa [Fri, 20 Dec 2024 12:31:28 +0000 (13:31 +0100)]
ggml : add test for SVE and disable when it fails (#10906)
Molly Sophia [Fri, 20 Dec 2024 09:44:58 +0000 (17:44 +0800)]
convert : fix RWKV v6 model conversion (#10913)
* Enable --no-context-shift for llama-perplexity example
Signed-off-by: Molly Sophia <redacted>
* RWKV 6: Fix error in ggml_cuda_op_bin_bcast
Signed-off-by: Molly Sophia <redacted>
---------
Signed-off-by: Molly Sophia <redacted>
Georgi Gerganov [Thu, 19 Dec 2024 16:47:15 +0000 (18:47 +0200)]
clip : disable GPU support (#10896)
ggml-ci
Georgi Gerganov [Thu, 19 Dec 2024 15:42:13 +0000 (17:42 +0200)]
llama : minor grammar refactor (#10897)
ggml-ci
Georgi Gerganov [Thu, 19 Dec 2024 15:35:15 +0000 (17:35 +0200)]
tts : small QoL for easy model fetch (#10903)
Xuan Son Nguyen [Thu, 19 Dec 2024 14:40:08 +0000 (15:40 +0100)]
server : fix logprobs, make it OAI-compatible (#10783)
* server : fix logprobs, make it openai-compatible
* update docs
* add std::log
* return pre-sampling p
* sort before apply softmax
* add comment
* fix test
* set p for sampled token
* update docs
* add --multi-token-probs
* update docs
* add `post_sampling_probs` option
* update docs [no ci]
* remove --multi-token-probs
* "top_probs" with "post_sampling_probs"
* resolve review comments
* rename struct token_prob to prob_info
* correct comment placement
* fix setting prob for sampled token
Adrien Gallouët [Thu, 19 Dec 2024 13:20:41 +0000 (14:20 +0100)]
ggml: fix arm build with gcc (#10895)
Signed-off-by: Adrien Gallouët <redacted>
Sukriti Sharma [Thu, 19 Dec 2024 13:04:51 +0000 (06:04 -0700)]
llama : fix Roberta embeddings (#10856)
* fix: Use gpt2 tokenizer for roberta and add eos/bos tokens
Branch: RobertaTokenizer
Signed-off-by: Gabe Goodhart <redacted>
* fixes to position embeddings
Signed-off-by: Sukriti-Sharma4 <redacted>
* map roberta-bpe to gpt-2
Signed-off-by: Sukriti-Sharma4 <redacted>
* fix linting
Signed-off-by: Sukriti-Sharma4 <redacted>
---------
Signed-off-by: Gabe Goodhart <redacted>
Signed-off-by: Sukriti-Sharma4 <redacted>
Co-authored-by: Gabe Goodhart <redacted>
fairydreaming [Thu, 19 Dec 2024 09:37:12 +0000 (10:37 +0100)]
convert : Add support for Microsoft Phi-4 model (#10817)
* convert : use GPT2 vocab for Phi-4 model
* convert : use null value of sliding_window to distinguish Phi-4 from other PHI3-based models
* llama : do not use sliding window attention mask for Phi-4 model
---------
Co-authored-by: Stanisław Szymczyk <redacted>
Johannes Gäßler [Thu, 19 Dec 2024 07:53:58 +0000 (08:53 +0100)]
tests: disable GGUF test for bad value size (#10886)
Eric Curtin [Thu, 19 Dec 2024 02:58:00 +0000 (02:58 +0000)]
llama-run : improve progress bar (#10821)
Set default width to whatever the terminal is. Also fixed a small bug around
default n_gpu_layers value.
Signed-off-by: Eric Curtin <redacted>
Diego Devesa [Wed, 18 Dec 2024 22:21:42 +0000 (23:21 +0100)]
ggml : fix arm build (#10890)
* ggml: GGML_NATIVE uses -mcpu=native on ARM
Signed-off-by: Adrien Gallouët <redacted>
* ggml: Show detected features with GGML_NATIVE
Signed-off-by: Adrien Gallouët <redacted>
* remove msvc support, add GGML_CPU_ARM_ARCH option
* disable llamafile in android example
* march -> mcpu, skip adding feature macros
ggml-ci
---------
Signed-off-by: Adrien Gallouët <redacted>
Co-authored-by: Adrien Gallouët <redacted>
Georgi Gerganov [Wed, 18 Dec 2024 17:27:21 +0000 (19:27 +0200)]
tts : add OuteTTS support (#10784)
* server : add "tokens" output
ggml-ci
* server : output embeddings for all tokens when pooling = none
ggml-ci
* server : be explicit about the pooling type in the tests
ggml-ci
* server : do not normalize embeddings when there is no pooling
ggml-ci
* llama : add OuteTTS support (wip)
* wip
* extract features
* first conv
* group norm
* resnet conv
* resnet
* attn
* pos net
* layer norm
* convnext
* head
* hann window
* fix n_embd + remove llama.cpp hacks
* compute hann window
* fft
* spectrum processing
* clean-up
* tts : receive input text and generate codes
* clip : fix new conv name
* tts : minor fix
* tts : add header + minor fixes
ggml-ci
* tts : add matchematical constant
ggml-ci
* tts : fix sampling + cut initial noise
* tts : fixes
* tts : update default samplers
ggml-ci
* tts : text pre-processing
* tts : outetts-voc -> wavtokenizer-dec
* tts : remove hardcoded constants
ggml-ci
* tts : fix tensor shapes
* llama : refactor wavtokenizer tensors
ggml-ci
* cont
ggml-ci
* cont [no ci]
* llama : update WavTokenizer to non-causal attn
* llama : handle no-vocab detokenization
* tts : add Python example for OuteTTS (wip)
* tts : extend python example to generate spectrogram
ggml-ci
* server : fix rebase artifacts
* tts : enable "return_tokens" in Python example
ggml-ci
* tts : minor fixes
* common : support HF download for vocoder
Gaetan Bisson [Wed, 18 Dec 2024 14:00:07 +0000 (04:00 -1000)]
server: avoid overwriting Authorization header (#10878)
* server: avoid overwriting Authorization header
If no API key is set, leave the Authorization header as is. It may be
used by another part of the Web stack, such as an authenticating proxy.
Fixes https://github.com/ggerganov/llama.cpp/issues/10854
* rebuild
---------
Co-authored-by: Xuan Son Nguyen <redacted>
Georgi Gerganov [Wed, 18 Dec 2024 11:01:41 +0000 (13:01 +0200)]
server : output embeddings for all tokens when pooling = none (#10861)
* server : add "tokens" output
ggml-ci
* server : output embeddings for all tokens when pooling = none
ggml-ci
* server : update readme [no ci]
* server : fix spacing [no ci]
Co-authored-by: Xuan Son Nguyen <redacted>
* server : be explicit about the pooling type in the tests
ggml-ci
* server : update /embeddings and /v1/embeddings endpoints
ggml-ci
* server : do not normalize embeddings when there is no pooling
ggml-ci
* server : update readme
ggml-ci
* server : fixes
* tests : update server tests
ggml-ci
* server : update readme [no ci]
* server : remove rebase artifact
---------
Co-authored-by: Xuan Son Nguyen <redacted>
Georgi Gerganov [Wed, 18 Dec 2024 09:05:29 +0000 (11:05 +0200)]
server : add "tokens" output (#10853)
* server : add "tokens" output
ggml-ci
* server : update readme
ggml-ci
* server : return tokens ids only if requested
ggml-ci
* tests : improve "tokens" type check
Co-authored-by: Xuan Son Nguyen <redacted>
* server : remove "tokens" from the OAI endpoint
ggml-ci
---------
Co-authored-by: Xuan Son Nguyen <redacted>
Xuan Son Nguyen [Wed, 18 Dec 2024 08:55:09 +0000 (09:55 +0100)]
server : (embeddings) using same format for "input" and "content" (#10872)
* server : (embeddings) using same format for "input" and "content"
* fix test case
* handle empty input case
* fix test
redbeard [Wed, 18 Dec 2024 08:35:00 +0000 (00:35 -0800)]
docs: Fix HIP (née hipBLAS) in README (#10880)
Related to #10524 /
be0e350c references to hipBLAS have been removed
across the repository. This fixes the link from the repositories
`README.md`.
Signed-off-by: Brian 'redbeard' Harrington <redacted>
Diego Devesa [Wed, 18 Dec 2024 00:36:46 +0000 (01:36 +0100)]
Revert "llama : add Falcon3 support (#10864)" (#10876)
This reverts commit
382bc7f2e8ffd0b89f23e840d097e21f301197ba .
DAN™ [Tue, 17 Dec 2024 22:24:22 +0000 (17:24 -0500)]
Use model->gguf_kv for loading the template instead of using the C API. (#10868)
* Bump model_template to 16384 bytes to support larger chat templates.
* Use `model->gguf_kv` for efficiency.
Johannes Gäßler [Tue, 17 Dec 2024 18:09:35 +0000 (19:09 +0100)]
tests: add tests for GGUF (#10830)
Georgi Gerganov [Tue, 17 Dec 2024 16:36:02 +0000 (18:36 +0200)]
sync : ggml
Georgi Gerganov [Tue, 17 Dec 2024 16:34:32 +0000 (18:34 +0200)]
cmake : fix "amd64" processor string (whisper/2638)
gn64 [Mon, 16 Dec 2024 10:34:38 +0000 (19:34 +0900)]
vulkan : fix soft_max.comp division by zero (whisper/2633)
This change prevents a division by zero error when p.KY is 0.
Daniel Bevenius [Sat, 14 Dec 2024 02:23:08 +0000 (03:23 +0100)]
ggml : remove return from ggml_gallocr_allocate_node (ggml/1048)
This commit removes the return statement from ggml_gallocr_allocate_node
function.
The motivation behind this change is to make the code more readable and
consistent.
Daniel Bevenius [Fri, 13 Dec 2024 07:19:38 +0000 (08:19 +0100)]
ggml : add check for grad_accs (ggml/1046)
* ggml : add check for grad_accs
This commit adds a check for grad_accs in ggml_graph_get_grad and
ggml_graph_get_grad_acc functions. This is necessary to avoid segfaults
when grad_accs is not initialized.
The motivation for this change is that I find it nice to be able to
print out a computation graph using ggml_graph_print but this function
segfaults when grad_accs is not initialized:
```console
(gdb) p g1
$2 = (ggml_cgraph *) 0x7ffff66004b0
(gdb) p *g1
$3 = {size = 2048, n_nodes = 1, n_leafs = 2, nodes = 0x7ffff6600500,
grads = 0x0, grad_accs = 0x0, leafs = 0x7ffff6604500,
visited_hash_set = {size = 4099, used = 0x7ffff6610518,
keys = 0x7ffff6608500}, order = GGML_CGRAPH_EVAL_ORDER_LEFT_TO_RIGHT}
(gdb) p ggml_graph_print(g1)
=== GRAPH ===
n_nodes = 1
Program received signal SIGSEGV, Segmentation fault.
0x0000555555579775 in ggml_graph_get_grad
(cgraph=0x7ffff66004b0,node=0x7ffff6600340)
at /ggml/ggml/src/ggml.c:5990
5990 return igrad != GGML_HASHSET_FULL &&
ggml_bitset_get(cgraph->visited_hash_set.used, igrad) ?
cgraph->grads[igrad] : NULL;
```
* squash! ggml : add check for grad_accs
Fix the check in ggml_graph_get_grad. The check was incorrectly using
cgraph->grad_accs instead of cgraph->grads.
Georgi Gerganov [Tue, 17 Dec 2024 16:35:42 +0000 (18:35 +0200)]
ggml : update ggml_backend_cpu_device_supports_op (#10867)
* ggml : fix cpy op for IQ-quants to use reference impl
ggml-ci
* ggml : disable tests involving i-matrix quantization
* ggml : update ggml_backend_cpu_device_supports_op
ggml-ci
krystiancha [Tue, 17 Dec 2024 16:00:24 +0000 (16:00 +0000)]
server : fill usage info in embeddings and rerank responses (#10852)
* server : fill usage info in embeddings response
* server : fill usage info in reranking response
Billel Mokeddem [Tue, 17 Dec 2024 15:24:56 +0000 (19:24 +0400)]
llama : add Falcon3 support (#10864)
Ruan [Tue, 17 Dec 2024 09:47:20 +0000 (17:47 +0800)]
readme : update typos (#10863)
Xuan Son Nguyen [Tue, 17 Dec 2024 08:52:09 +0000 (09:52 +0100)]
server : (UI) fix missing async generator on safari (#10857)
* server : (UI) fix missing async generator on safari
* fix
Eve [Tue, 17 Dec 2024 05:52:55 +0000 (05:52 +0000)]
vulkan: bugfixes for small subgroup size systems + llvmpipe test (#10809)
* ensure mul mat shaders work on systems with subgroup size less than 32
more fixes
add test
* only s_warptile_mmq needs to be run with 32 threads or more
Zhiyuan Li [Mon, 16 Dec 2024 21:00:46 +0000 (05:00 +0800)]
rwkv6: add wkv6 support for Vulkan backend (#10829)
* rwkv_wkv6 vulkan shader
* RWKV_WKV6 Vulkan op tests passed
Signed-off-by: Molly Sophia <redacted>
* Apply code format changes
Signed-off-by: Molly Sophia <redacted>
* add [[unroll]] and remove unnecessary conditions
* add uma support
* fix erros in EditorConfig Checker
---------
Signed-off-by: Molly Sophia <redacted>
Co-authored-by: Molly Sophia <redacted>
Georgi Gerganov [Mon, 16 Dec 2024 10:31:45 +0000 (12:31 +0200)]
unicode : improve naming style (#10838)
* unicode : improve naming style
ggml-ci
* cont [no ci]
Georgi Gerganov [Mon, 16 Dec 2024 10:31:14 +0000 (12:31 +0200)]
sampling : refactor + optimize penalties sampler (#10803)
* sampling : refactor + optimize penalties sampler
ggml-ci
* common : apply ignore_eos as logit bias
ggml-ci
* batched : remove penalties sampler
* params : allow penalty_last_n == -1 to be equal to context size
ggml-ci
* common : by default, move the penalties at the end of the sampling chain
ggml-ci
* common : ignore all EOG tokens
Co-authored-by: Diego Devesa <redacted>
* common : move back the penalties at the front of the sampling chain
ggml-ci
* readme : restore hint about --ignore-eos flag [no ci]
* llama : minor
ggml-ci
* webui : update
---------
Co-authored-by: Diego Devesa <redacted>
Bartowski [Sun, 15 Dec 2024 20:43:25 +0000 (15:43 -0500)]
llava : Allow locally downloaded models for QwenVL (#10833)
* Allow locally downloaded models for QwenVL
* Define model_path
* rm trailing space
---------
Co-authored-by: Xuan Son Nguyen <redacted>
Valentin Mamedov [Sun, 15 Dec 2024 17:02:46 +0000 (00:02 +0700)]
llama : add Deepseek MoE v1 & GigaChat models (#10827)
* Add deepseek v1 arch & gigachat template
* improve template code
* add readme
* delete comments
* remove comment
* fix format
* lint llama.cpp
* fix order of deepseek and deepseek2, move gigachat temlate to the end of func
* fix order of deepseek and deepseek2 in constants; mark shared exp as deepseek arch need
* remove comments
* move deepseek above deepseek2
* change placement of gigachat chat template
Georgi Gerganov [Sun, 15 Dec 2024 16:44:47 +0000 (18:44 +0200)]
scripts : change build path to "build-bench" for compare-commits.sh (#10836)
Vinesh Janarthanan [Sun, 15 Dec 2024 11:55:54 +0000 (05:55 -0600)]
server: (UI) add syntax highlighting and latex math rendering (#10808)
* add code highlighting and math formatting
* code cleanup
* build public/index.html
* rebuild public/index.html
* fixed coding style
* fixed coding style
* style fixes
* highlight: smaller bundle size, fix light & dark theme
* remove katex
* add bundle size check
* add more languages
* add php
* reuse some langs
* use gzip
* Revert "remove katex"
This reverts commit
c0e5046accd10be3f83018cffdc29a652849fc61 .
* use better maintained @vscode/markdown-it-katex
* fix gzip non deterministic
* ability to add a demo conversation for dev
* fix latex rendering
* add comment
* latex codeblock as code
---------
Co-authored-by: Xuan Son Nguyen <redacted>
Georgi Gerganov [Sun, 15 Dec 2024 11:16:42 +0000 (13:16 +0200)]
gguf-py : bump to v0.13.0
Michelle Tan [Sat, 14 Dec 2024 22:29:45 +0000 (22:29 +0000)]
server: Fix `has_next_line` in JSON response (#10818)
* Update server JSON response.
* Add unit test to check `has_new_line` JSON response
* Remove `has_new_line` unit test changes.
* Address code review comment: type check for `has_new_line` in unit test
Evgeny Kurnevsky [Sat, 14 Dec 2024 18:17:36 +0000 (18:17 +0000)]
nix: allow to override rocm gpu targets (#10794)
This allows to reduce compile time when you are building for a single GPU.
HimariO [Sat, 14 Dec 2024 12:43:46 +0000 (20:43 +0800)]
llama : add Qwen2VL support + multimodal RoPE (#10361)
* Barebone Qwen2VL LLM convertor
* Add Qwen2VL cli entrypoint
* [WIP] add qwen2vl arch
* Verify m-rope output
* Add vl-rope/2d-rope support for qwen2vl ViT
* update qwen2vl cli tool
* update 5D tensor op workaround
* [WIP] qwen2vl vision model
* make batch and clip utils compatible with qwen2vl
* [WIP] create inference workflow, gguf convert script but fix
* correcting vision-rope behavior, add the missing last layer back to ViT
* add arg parser to qwen2vl_surgery
* replace variable size array with vector
* cuda-gdb cmake preset
* add fp32 mrope, vision rope kernel
* add fp16 support for qwen2vl and m-rope
* add `GGML_ROPE_TYPE_MROPE`, `GGML_ROPE_TYPE_VISION`
* fix rope op mode switching, out dated func args
* update `llama_hparams`
* update to keep up stream changes
* resolve linter, test errors
* add makefile entry, update speical image padding token
* add mrope unit test, fix few compiler warnings
* rename `mrope` related function, params
* minor updates on debug util, bug fixs
* add `m-rope` testcase to `test-backend-ops`
* Apply suggestions from code review
Co-authored-by: Georgi Gerganov <redacted>
* fix traililng whitespce
* store `llama_hparams.rope_sections` with fixed size array
* update position id tensor size check in GGML_OP_ROPE
* minor updates
* update `ggml_backend_*_supports_op` of unsupported backends
* remote old `rope_section` compare operator
---------
Co-authored-by: Georgi Gerganov <redacted>
cduk [Fri, 13 Dec 2024 22:21:49 +0000 (23:21 +0100)]
Removes spurious \r in output that causes logging in journalctl to treat lines as binary and therefore hidden by default (#10771)
Signed-off-by: Charles Darke <redacted>
Co-authored-by: Charles Darke <redacted>
lhez [Fri, 13 Dec 2024 20:23:52 +0000 (12:23 -0800)]
Introducing experimental OpenCL backend with support for Qualcomm Adreno GPUs (#10693)
* [cl][adreno] Add Adreno GPU support
Add new OpenCL backend to support Adreno GPUs
---------
Co-authored-by: Skyler Szot <redacted>
Co-authored-by: Shangqing Gu <redacted>
Co-authored-by: Alexander Angus <redacted>
Co-authored-by: Hongqiang Wang <redacted>
Co-authored-by: Max Krasnyansky <redacted>
* [cl][ci] Add workflow for CL
* [cl][adreno] Fix memory leak for non SMALL_ALLOC path
* opencl: integrate backend dyn.load interface and fix compiler and format warnings
* opencl: remove small-alloc support and fix build errors for non-opencl platforms
* opencl: fixed merge conflict (MUSA added twice in cmake)
* opencl-ci: use RUNNER_TEMP instead of github.workspace
* opencl: fix embed tool invocation with python3
* opencl: CI workflow fixes
* opencl: Clean up small-alloc in CMake files
* opencl: cleanup ggml-opencl2 header file
* opencl: use ulong for offsets and strides in ADD kernel
* opencl: use cl_ulong for all offsets
* opencl: use cl_ulong for sizes and strides
* opencl: use `GGML_LOG_xxx` instead of `fprintf(stderr, ...)`
* opencl: rename backend `opencl2` -> `opencl`
* opencl: rename kernel files `ggml-opencl2` -> `ggml-opencl`
* opencl: make OpenCL required, remove redundant lib and inc directories
* `ggml-base`, `..` and `.` are added by `ggml_add_backend_library`
* opencl: rename backend - funcs, structs, etc `opencl2` -> `opencl`
* opencl: remove copyright marker since main license already covers
* opencl: replace some more OPENCL2 leftovers
* opencl: remove limits on `tensor_extra`
* opencl: use pools for `tensor_extra`
* opencl: fix compiler warnings with GCC and Clang
Still getting the warning about clCreateCmdQueue being obsolete.
Will fix that separately.
* opencl: fail gracefully if opencl devices are not available
Also for unsupported GPUs.
* opencl: fix MSVC builds (string length error)
* opencl: check for various requirements, allow deprecated API
* opencl: update log message for unsupported GPUs
---------
Co-authored-by: Skyler Szot <redacted>
Co-authored-by: Shangqing Gu <redacted>
Co-authored-by: Alexander Angus <redacted>
Co-authored-by: Hongqiang Wang <redacted>
Co-authored-by: Max Krasnyansky <redacted>
Eric Curtin [Fri, 13 Dec 2024 18:34:25 +0000 (18:34 +0000)]
Opt class for positional argument handling (#10508)
Added support for positional arguments `model` and `prompt`. Added
functionality to download via strings like:
llama-run llama3
llama-run ollama://granite-code
llama-run ollama://granite-code:8b
llama-run hf://QuantFactory/SmolLM-135M-GGUF/SmolLM-135M.Q2_K.gguf
llama-run huggingface://bartowski/SmolLM-1.7B-Instruct-v0.2-GGUF/SmolLM-1.7B-Instruct-v0.2-IQ3_M.gguf
llama-run https://example.com/some-file1.gguf
llama-run some-file2.gguf
llama-run file://some-file3.gguf
Signed-off-by: Eric Curtin <redacted>
Corentin REGAL [Fri, 13 Dec 2024 17:23:50 +0000 (18:23 +0100)]
fix: graceful shutdown for Docker images (#10815)
Jett Janiak [Fri, 13 Dec 2024 14:48:44 +0000 (15:48 +0100)]
gguf-py : numpy 2 newbyteorder fix (#9772)
谢乃闻 [Fri, 13 Dec 2024 12:56:07 +0000 (12:56 +0000)]
Fix crash caused by ggml_backend_load_all when launching on Android Activity (#10812)
* Fix crash caused by ggml_backend_load_all when launching on AndroidActivity.
Details:
Calling ggml_backend_load_all during initialization in the AndroidActivity project leads to a crash with the error:
terminating with uncaught exception of type std::__ndk1::__fs::filesystem::filesystem_error: filesystem error: in directory_iterator::directory_iterator(...): Permission denied [./].
This issue occurs because AndroidActivity restricts file access due to sandboxing.
Reproduction:
In the example folder, the LlamaAndroid project can reproduce the crash by calling ggml_backend_load_all first in Java_android_llama_cpp_LLamaAndroid_backend_1init.
* Update ggml/src/ggml-backend-reg.cpp
---------
Co-authored-by: Diego Devesa <redacted>
Eve [Fri, 13 Dec 2024 08:42:04 +0000 (08:42 +0000)]
vulkan: small mul_mat_vec optimizations (#10665)
* double the number of rows per workgroup
* Update ggml-vulkan.cpp
* Vulkan: Add VK_EXT_subgroup_size_control support to ensure full subgroups for coopmats
* only increase the number of rows for amd and subgroup size 64
* fix missing NUM_ROWS for mul_mat_vec_iq4_nl_f16_f32, untested
* use subgroup min and max to check for gcn (requires https://github.com/ggerganov/llama.cpp/pull/10721)
* manual merge ggml-vulkan.cpp
* set min and max subgroup size in any case
* Also double the number of rows for Intel GPUs
Akarshan Biswas [Fri, 13 Dec 2024 06:42:15 +0000 (12:12 +0530)]
SYCL: Reduce most of the compiler warnings (#10748)
* Try to reduce some unused and typecast warnings
* Reduce compiler warnings step 2
* add a newline at the end of the file
* Initialize nreduce as size_t
* [SYCL] Remove pragma directives from mmq.cpp
* SYCL: mmq add condition to prevent blocks_per_tile_x_row variable from becoming 0
* SYCL softmax: Initialize nreduce as size_t
* ggml-sycl.cpp: fix some trailing whitespaces
* SYCL: remove the unused variables instead of commenting it out
* SYCL poo2d kernel: set NAN for invalid pooling op
* SYCL gemm.hpp: remove pragma directives
* SYCL gemm.hpp: use const cast to properly support dnnl::memory
* SYCL: wkv6 remove a comment
* SYCL: clean comments step 2
* SYCL: clean comments and variables step 3
* SYCL: Use GGML_UNUSED for unused variables
* SYCL: remove extra empty lines and a comment
* Remove TODO
* cleanup spaces
* add a stdout for unsupported op
* use sycl printf over fprintf
* remove prints for CI
* SYCL ggml-sycl: pool2D use sycl::nan and remove if-else block
---------
Co-authored-by: Abhilash Majumder <redacted>
Karol Kontny [Fri, 13 Dec 2024 00:04:19 +0000 (01:04 +0100)]
ggml : Fix compilation issues on ARM platform when building without fp16 (#10811)
Xuan Son Nguyen [Thu, 12 Dec 2024 21:53:05 +0000 (22:53 +0100)]
common : improve -ctv -ctk CLI arguments (#10806)
* common : improve ctv ctk cli argument
* regenerate docs
* even better approach
* use std::vector
Xuan Son Nguyen [Thu, 12 Dec 2024 19:52:28 +0000 (20:52 +0100)]
contrib : add ngxson as codeowner (#10804)
a3sh [Thu, 12 Dec 2024 18:09:50 +0000 (02:09 +0800)]
CUDA: faster non-contiguous concat (#10760)
* faster uncontiguous concat
* Use a lambda to avoid code duplication
Co-authored-by: Diego Devesa <redacted>
* Update ggml/src/ggml-cuda/concat.cu
* add constexpr and static assert
---------
Co-authored-by: Diego Devesa <redacted>
Diego Devesa [Thu, 12 Dec 2024 18:02:49 +0000 (19:02 +0100)]
remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (#10797)
other windows build fixes
0cc4m [Thu, 12 Dec 2024 17:36:00 +0000 (18:36 +0100)]
Vulkan: Use improved q4_k and q5_k dequant code in dequant shaders (#10798)
0cc4m [Thu, 12 Dec 2024 17:35:37 +0000 (18:35 +0100)]
Vulkan: Add VK_EXT_subgroup_size_control support to ensure full subgroups for coopmats (#10721)
* Vulkan: Add VK_EXT_subgroup_size_control support to ensure full subgroups for coopmats
* Fix subgroup size control extension support check
Add accf32 and accf16 checks for coopmats
* Also disable coopmats on amdvlk
Xuan Son Nguyen [Thu, 12 Dec 2024 15:57:32 +0000 (16:57 +0100)]
common : add missing env var for speculative (#10801)
CentricStorm [Wed, 11 Dec 2024 22:40:40 +0000 (22:40 +0000)]
docs: update server streaming mode documentation (#9519)
Provide more documentation for streaming mode.
Georgi Gerganov [Wed, 11 Dec 2024 21:14:46 +0000 (23:14 +0200)]
Merge pull request #10788 from ggerganov/gg/gguf-py-0.11.0
Georgi Gerganov [Wed, 11 Dec 2024 21:13:31 +0000 (23:13 +0200)]
gguf-py : bump version to 0.11.0
Xuan Son Nguyen [Wed, 11 Dec 2024 19:52:14 +0000 (20:52 +0100)]
server : (UI) add tok/s, get rid of completion.js (#10786)
* get rid of completion.js
* extract chat bubble to a component
* add tok/s info
* sync
* fix BASE_URL
* only extract timings when it's enabled
* fix auto scroll
qingy1337 [Wed, 11 Dec 2024 15:16:32 +0000 (07:16 -0800)]
Update README.md (#10772)
Xuan Son Nguyen [Wed, 11 Dec 2024 13:59:41 +0000 (14:59 +0100)]
ci : pin nodejs to 22.11.0 (#10779)
kallewoof [Wed, 11 Dec 2024 13:48:04 +0000 (22:48 +0900)]
bug-fix: snprintf prints NULL in place of the last character (#10419)
* bug-fix: snprintf prints NULL in place of the last character
We need to give snprintf enough space to print the last character and the null character, thus we allocate one extra byte and then ignore it when converting to std::string.
* add comment about extra null-term byte requirement
CentricStorm [Wed, 11 Dec 2024 10:47:43 +0000 (10:47 +0000)]
docs: fix server documentation formatting (#10776)
Gilad S. [Wed, 11 Dec 2024 00:47:21 +0000 (02:47 +0200)]
ggml: load all backends from a user-provided search path (#10699)
* feat: load all backends from a user-provided search path
* fix: Windows search path
* refactor: rename `ggml_backend_load_all_in_search_path` to `ggml_backend_load_all_from_path`
* refactor: rename `search_path` to `dir_path`
* fix: change `NULL` to `nullptr`
Co-authored-by: Diego Devesa <redacted>
* fix: change `NULL` to `nullptr`
---------
Co-authored-by: Diego Devesa <redacted>
Jeff Bolz [Tue, 10 Dec 2024 20:23:17 +0000 (14:23 -0600)]
vulkan: request round-to-even for fp16 in im2col/rope_head (#10767)
Vulkan doesn't mandate a specific rounding mode, but the shader_float_controls
feature allows rounding mode to be requested if the implementation supports it.
Eve [Tue, 10 Dec 2024 19:33:23 +0000 (19:33 +0000)]
vulkan: dynamic subgroup size for the remaining k quants (#10745)
* q5_k
q4_k
q3_k
q2_k
q6_k multi row example
* revert as multi row isnt faster for k quants
Bartowski [Tue, 10 Dec 2024 17:23:50 +0000 (12:23 -0500)]
imatrix : Add imatrix to --no-context-shift (#10766)
This allows for setting the --no-context-shift value in llama-imatrix which is required for models like DeepSeek
Andreas Kieslinger [Tue, 10 Dec 2024 17:23:24 +0000 (18:23 +0100)]
CUDA: rename macros to avoid conflicts with WinAPI (#10736)
* Renames NVIDIA GPU-architecture flags to avoid name clashes with WinAPI. (e.g. CC_PASCAL, GPU architecture or WinAPI pascal compiler flag?)
* Reverts erroneous rename in SYCL-code.
* Renames GGML_CUDA_MIN_CC_DP4A to GGML_CUDA_CC_DP4A.
* Renames the rest of the compute capability macros for consistency.
Yüg [Tue, 10 Dec 2024 17:22:34 +0000 (17:22 +0000)]
server : add flag to disable the web-ui (#10762) (#10751)
Co-authored-by: eugenio.segala <redacted>
Jeff Bolz [Tue, 10 Dec 2024 17:22:20 +0000 (11:22 -0600)]
vulkan: disable spirv-opt for coopmat shaders (#10763)
There are some bugs in the 1.3.296 SDK, so disable this. It isn't strictly
necessary anyway.
Add missing dependency on vulkan-shaders-gen, so shaders get recompiled when it
changes.
Fix coopmat support reporting when glslc doesn't support NV_coopmat2.
Johannes Gäßler [Mon, 9 Dec 2024 19:07:12 +0000 (20:07 +0100)]
CUDA: fix shared memory access condition for mmv (#10740)
Srihari-mcw [Mon, 9 Dec 2024 17:40:19 +0000 (23:10 +0530)]
Changes to CMakePresets.json to add ninja clang target on windows (#10668)
* Update cmakepreset.json to use clang with ninja by default
* Update cmakepreset.json to add clang and ninja based configs
* Updates to build.md file
* Make updates to rename preset targets
* Update with .cmake file
* Remove additional whitespaces
* Add .cmake file for x64-windows-llvm
* Update docs/build.md
* Update docs/build.md
---------
Co-authored-by: Max Krasnyansky <redacted>
Jeff Bolz [Mon, 9 Dec 2024 07:24:01 +0000 (01:24 -0600)]
vulkan: fix compile warnings (#10731)
Borislav Stanimirov [Mon, 9 Dec 2024 07:15:13 +0000 (09:15 +0200)]
cmake : simplify msvc charsets (#10672)
Xuan Son Nguyen [Sun, 8 Dec 2024 22:04:29 +0000 (23:04 +0100)]
server : fix format_infill (#10724)
* server : fix format_infill
* fix
* rename
* update test
* use another model
* update test
* update test
* test_invalid_input_extra_req
Xuan Son Nguyen [Sun, 8 Dec 2024 19:38:51 +0000 (20:38 +0100)]
server : bring back info of final chunk in stream mode (#10722)
* server : bring back into to final chunk in stream mode
* clarify a bit
* traling space
stduhpf [Sun, 8 Dec 2024 18:19:19 +0000 (19:19 +0100)]
Vulkan: fix NaN in tanh.comp with AMD proprietary driver on Windows (#10723)
* Vulkan: fix NaN in tanh.comp
* Faster NaN-free tanh