ollama/llama/ggml-cuda/template-instances
Gabe Goodhart f2890a4494
IBM granite/granitemoe architecture support (#6760)
* fix(ext_server): Port llama.cpp sampling refactors to ext_server

This was a fairly large changeset. I closely followed the changes here:
df270ef745

Branch: IBMGraniteArchitectureSupport

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(server.cpp): Refactor server.cpp logging for llama.cpp overhaul

Branch: IBMGraniteArchitectureSupport

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* feat: Bump llama.cpp to the latest master with `granite` support

This does not yet have granite MoE support, but that can come in a
follow up PR

Branch: IBMGraniteArchitectureSupport

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(patches): Update all patches (except solar-pro) to work with bumped llama.cpp

Branch: IBMGraniteArchitectureSupport

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(solar): Update solar patch for llama.cpp bump

Branch: IBMGraniteArchitectureSupport

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* feat(llama.cpp): Bump llama.cpp for granitemoe support

Branch: IBMGraniteArchitectureSupport

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* feat(llama.cpp): Bump llama.cpp for granitemoe support

Branch: IBMGraniteArchitectureSupport

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(solar): Update the solar-pro patch for latest llama.cpp bump

Branch: IBMGraniteArchitectureSupport

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* feat(llama.cpp): Bump to the latest master of llama.cpp

Branch: IBMGraniteArchitectureSupport

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(patches): Update all patches for latest bump

Branch: IBMGraniteArchitectureSupport

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* feat(llama): Always run sync.sh from the right directory

Branch: IBMGraniteArchitectureSupport

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(llama/patches): Update llama patches

Branch: IBMGraniteArchitectureSupport

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* feat(llama)!: Rough sync with llama.cpp submodule

There are a number of changes that will need to be propagated to llama.go
before any of this works!

Branch: IBMGraniteArchitectureSupport

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(llama/patches): Add a patch and update for missing ggml-impl.h include

This include is where the ggml_cgraph struct is defined. It is included in
many of the .c files to define the forward declartion in ggml.h. It seems
that with the subset of code included here, the import was somehow lost (or
out-of-order) when building, so adding this include to llama.cpp fixes the
missing definition.

Branch: IBMGraniteArchitectureSupport

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(llama/sync): Add missing ggml-cpu-impl.h copy-over in sync.sh

Branch: IBMGraniteArchitectureSupport

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(llama): Add missing log.cpp

This was added as part of the logging overhaul done in llama.cpp

Branch: IBMGraniteArchitectureSupport

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(llama): Overhaul use of sampling module for llama.cpp changes

The changes here reflect the changes made in the big llama.cpp sampling PR
https://github.com/ggerganov/llama.cpp/pull/9294

The sampling functionality is now broken into the base interface
(llama_sampler) and the generation implementation (gpt_sampler). The
changes here reflect that. Since the sampling.h/sampling.cpp code uses c++
STL headers, the sampling_ext.[h|cpp] wrapper is maintained to allow go to
access a pure-C interface.

Branch: IBMGraniteArchitectureSupport

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(llama): Fix the impl of SampleTokenGreedy for new sampling

I don't think this method is currently used, so it could probably just be
removed so that all sampling goes through the GPT interface, but in the
interest of doing no harm, this should keep the method working as expected.

Branch: IBMGraniteArchitectureSupport

* fix(llama): Remove unused SampleTokenGreedy

Branch: IBMGraniteArchitectureSupport

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(sync): Remove bash-specific change to sync.sh

Branch: IBMGraniteArchitectureSupport

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* chore(gofumpt): Format on llama.go to pass linting

Branch: IBMGraniteArchitectureSupport

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(llm): Fix missing <thread> include in ext_server

Branch: IBMGraniteArchitectureSupport

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(llama): Remove TODO about grammar_first

This feature was not used/needed previously so should be fine without
plumbing it through now.

Branch: IBMGraniteArchitectureSupport

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(llama): Better naming for sampling wrapper and args

Branch: IBMGraniteArchitectureSupport

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(llama): Fix patch 05 to use new wrapper api and re-sync

Branch: IBMGraniteArchitectureSupport

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* runner: Flush pending responses before returning

If there are any pending reponses (such as from potential stop
tokens) then we should send them back before ending the sequence.
Otherwise, we can be missing tokens at the end of a response.

Fixes #6707

* fix(llama/sampling): Use gpt_sampler with a forward declaration

Branch: IBMGraniteArchitectureSupport

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(llama): Remove unnecessary patch for gguf impl header

This was caused by an earlier mistake in the embeddings patch that was
dereferencing the pointer instead of using the wrapper API.

Branch: IBMGraniteArchitectureSupport

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix(llm): Remove use of deprecated --log-disable flag

Branch: IBMGraniteArchitectureSupport

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

---------

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
2024-10-17 11:59:52 -07:00
..
fattn-vec-f16-instance-hs64-f16-f16.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs64-f16-q4_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs64-f16-q4_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs64-f16-q5_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs64-f16-q5_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs64-f16-q8_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-f16-f16.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-f16-q4_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-f16-q4_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-f16-q5_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-f16-q5_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-f16-q8_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q4_0-f16.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q4_0-q4_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q4_0-q4_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q4_0-q5_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q4_0-q5_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q4_0-q8_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q4_1-f16.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q4_1-q4_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q4_1-q4_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q4_1-q5_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q4_1-q5_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q4_1-q8_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q5_0-f16.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q5_0-q4_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q5_0-q4_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q5_0-q5_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q5_0-q5_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q5_0-q8_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q5_1-f16.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q5_1-q4_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q5_1-q4_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q5_1-q5_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q5_1-q5_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q5_1-q8_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q8_0-f16.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q8_0-q4_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q8_0-q4_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q8_0-q5_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q8_0-q5_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs128-q8_0-q8_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f16-instance-hs256-f16-f16.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs64-f16-f16.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs64-f16-q4_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs64-f16-q4_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs64-f16-q5_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs64-f16-q5_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs64-f16-q8_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-f16-f16.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-f16-q4_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-f16-q4_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-f16-q5_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-f16-q5_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-f16-q8_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q4_0-f16.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q4_0-q4_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q4_0-q4_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q4_0-q5_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q4_0-q5_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q4_0-q8_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q4_1-f16.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q4_1-q4_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q4_1-q4_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q4_1-q5_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q4_1-q5_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q4_1-q8_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q5_0-f16.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q5_0-q4_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q5_0-q4_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q5_0-q5_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q5_0-q5_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q5_0-q8_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q5_1-f16.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q5_1-q4_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q5_1-q4_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q5_1-q5_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q5_1-q5_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q5_1-q8_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q8_0-f16.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q8_0-q4_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q8_0-q4_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q8_0-q5_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q8_0-q5_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs128-q8_0-q8_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-vec-f32-instance-hs256-f16-f16.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-wmma-f16-instance-kqfloat-cpb16.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-wmma-f16-instance-kqfloat-cpb32.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-wmma-f16-instance-kqhalf-cpb8.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-wmma-f16-instance-kqhalf-cpb16.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
fattn-wmma-f16-instance-kqhalf-cpb32.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
mmq-instance-iq1_s.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
mmq-instance-iq2_s.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
mmq-instance-iq2_xs.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
mmq-instance-iq2_xxs.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
mmq-instance-iq3_s.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
mmq-instance-iq3_xxs.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
mmq-instance-iq4_nl.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
mmq-instance-iq4_xs.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
mmq-instance-q2_k.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
mmq-instance-q3_k.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
mmq-instance-q4_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
mmq-instance-q4_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
mmq-instance-q4_k.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
mmq-instance-q5_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
mmq-instance-q5_1.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
mmq-instance-q5_k.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
mmq-instance-q6_k.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00
mmq-instance-q8_0.cu IBM granite/granitemoe architecture support (#6760) 2024-10-17 11:59:52 -07:00